skill-doc-sync
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from project markdown files.
- Ingestion points: Up to 30 .md files are read from the project root and subdirectories.
- Boundary markers: None present.
- Capability inventory: Filesystem writes, git commit, and GitHub CLI interactions.
- Sanitization: None present.
- [COMMAND_EXECUTION]: The skill executes multiple local shell commands to automate its workflow.
- Evidence: Utilizes find for file discovery, git diff for change analysis, and gh pr view for pull request information.
- Context: These operations are scoped to documentation discovery and versioning consistency.
Audit Metadata