snap-scope
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it incorporates untrusted data from GitHub and the codebase into its reasoning process.
- Ingestion points: Fetches external content using
gh issue viewand performs codebase exploration as specified in SKILL.md. - Boundary markers: There are no explicit instructions to treat fetched data as untrusted or to use delimiters to prevent instruction leakage.
- Capability inventory: The skill is restricted to a 'thinking space' only; it is explicitly forbidden from making code changes or producing documents (SKILL.md), which limits the impact of potential injections.
- Sanitization: No sanitization, validation, or filtering of the retrieved content is performed.
Audit Metadata