docs-serverless-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local Markdown files and GitHub PR content (titles, bodies, and comments) to generate changelog entries. While this creates a potential injection surface, the risk is mitigated by the skill's specific task focus and restricted execution environment.
- Ingestion points: The raw Markdown tool output file and GitHub PR metadata fetched via the GitHub CLI.
- Boundary markers: None explicitly defined in the instructions to separate external data from system instructions.
- Capability inventory: Access is limited to
Read,Grep, andBash(gh *). The skill lacks file-write permissions or unrestricted shell/network capabilities. - Sanitization: Instructions do not mandate specific sanitization of external data.
- [COMMAND_EXECUTION]: Employs the GitHub CLI (
gh) to fetch repository context. Tool access is correctly limited in the skill configuration to theghcommand set, following the principle of least privilege.
Audit Metadata