043-planning-github-issues
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from GitHub issues and comments, which are untrusted external inputs.
- Ingestion points: External data is brought into the context via
gh issue listandgh issue viewcommands inreferences/043-planning-github-issues.md. - Boundary markers: There are no explicit delimiters or specific 'ignore' instructions for the retrieved data, although the instructions suggest treating the data as draft input for user review in Step 5.
- Capability inventory: The agent can execute
ghCLI commands and pass data to subsequent skills like@014-agile-user-story. - Sanitization: The skill lacks explicit sanitization or filtering logic for the content fetched from GitHub.
Audit Metadata