Loading the registry…
TypeScript code execution API for Canvas MCP
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
282 critical findings reported by cisco-skill-scanner, agent-audit-kit, 6 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from. Some sources have no verdict at all; that is not a pass.
github: https://github.com/vishalsachdev/canvas-mcp, 439 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- canvas-mcp-code-api
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
0 findings · 4.2s
v2.0.11
63 findings · 124.1s
v0.3.26
327 findings · 111.3s
v0.1.0
1 finding · 91.8s
v0.1.0
1 finding · 91.8s
v0.1.0
0 findings · 31.9s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 392 findings across every scanner that examined this package. 275 of 282 findings rated critical by their scanner were among the dismissals.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
272 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-001, AAK-AGENT-003, AAK-AGENT-002 and 2 more · Files: AGENTS.md, CLAUDE.md, /repo/repo/AGENTS.md and 1 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
41 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-SSRF-001, YARA_sql_injection_generic, YARA_script_injection_generic and 10 more · Files: tests/tools/test_modules.py, tests/tools/test_rubrics.py, tests/tools/test_courses.py and 12 more · reported by agent-audit-kit, cisco-skill-scanner
14 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_unicode_steganography, FILE_MAGIC_MISMATCH, HIDDEN_DATA_FILE and 2 more · Files: /repo/docs/drew-rozema.jpeg, /repo/docs/llms.txt, /repo/docs/.nojekyll and 4 more · reported by cisco-skill-scanner
12 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/claude-code-review.yml, .github/workflows/auto-label-issues.yml, .github/workflows/claude.yml and 5 more · reported by agent-audit-kit
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
17 MANIFEST_MISSING_LICENSE
Files: /repo/skills/canvas-course-builder/SKILL.md, /repo/skills/canvas-peer-review-manager/SKILL.md, /repo/skills/canvas-course-qc/SKILL.md and 14 more · reported by cisco-skill-scanner
9 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/cli/SKILL.md, /repo/internal/SKILL.md and 6 more · reported by cisco-skill-scanner
4 AAK-SSRF-005
Files: src/canvas_mcp/tools/accessibility.py, src/canvas_mcp/tools/student_write.py, src/canvas_mcp/tools/code_execution.py and 1 more · reported by agent-audit-kit
3 AAK-SSRF-001
Files: src/canvas_mcp/tools/accessibility.py, src/canvas_mcp/tools/student_write.py, src/canvas_mcp/tools/rubrics.py · reported by agent-audit-kit
3 YARA_command_injection_generic
Files: /repo/deploy/azure/README.md, /repo/deploy/azure/SKILL.md · reported by cisco-skill-scanner
Critical vulnerabilities found, including server-side request forgery and command injection.
The artifact contains critical server-side request forgery (SSRF) vulnerabilities in `src/canvas_mcp/tools/accessibility.py`, `src/canvas_mcp/tools/rubrics.py`, and `src/canvas_mcp/tools/student_write.py`, which could allow network requests to arbitrary destinations. High severity SSRF findings are also present in `src/canvas_mcp/tools/code_execution.py` and `src/canvas_mcp/tools/files.py`. Additionally, a critical command injection vulnerability is present in `src/canvas_mcp/tools/student_write.py`, enabling shell execution. The artifact also exhibits high severity network egress of secrets from `/repo/src/canvas_mcp/code_api/client.ts`.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
Files: internal/session-history.md, internal/issue-triage/2026-07-31.md · reported by agent-audit-kit
2 DATA_EXFIL_JS_NETWORK
Files: /repo/src/canvas_mcp/code_api/client.ts · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/articles/2026-02-23-the-moment-your-side-project-stops-being-yours.html · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/src/canvas_mcp/code_api, /repo/cli · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 AAK-MCP-015
Files: src/canvas_mcp/tools/student_write.py · reported by agent-audit-kit
1 AAK-MCP-018
Files: src/canvas_mcp/server.py · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SSRF-004
Files: src/canvas_mcp/tools/files.py · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.mcpbignore · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/src/canvas_mcp/code_api/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/canvas_mcp/code_api/client.ts · reported by nerlo-behavioral