codewiki-generator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/codewiki_analyze.py executes several system commands using subprocess.run to extract metadata from the target repository.
  • It invokes go list, cargo metadata, swift package, and ctags within the repository directory to identify dependencies and symbols.
  • [EXTERNAL_DOWNLOADS]: The skill depends on external Node.js packages and CLIs to build and deploy the documentation site.
  • The workflow in SKILL.md triggers npm install and npx to manage VitePress and its plugins.
  • The deployment instructions in references/deploy-cloudflare.md recommend installing the wrangler CLI from the npm registry.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it interprets and processes content from the analyzed codebase.
  • Ingestion points: scripts/codewiki_analyze.py reads source code, package.json, README.md, and other text files from the target repository.
  • Boundary markers: While generated documentation includes # Related Code markers, there are no explicit instructions to the LLM to ignore embedded commands within the analyzed source data.
  • Capability inventory: The skill can perform file system writes and execute subprocesses (npm, npx, wrangler) based on the documentation plan.
  • Sanitization: There is no sanitization or filtering of the repository's content before it is processed by the agent to generate documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:36 PM