repro-issue
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue descriptions and comments, which constitutes a surface for indirect prompt injection.\n
- Ingestion points: External data is retrieved using the
gh issue viewandgh pr viewcommands as described inSKILL.md.\n - Boundary markers: The workflow lacks explicit boundary markers or instructions to ignore potential commands embedded within the retrieved GitHub content.\n
- Capability inventory: The agent uses shell commands for issue retrieval and performs file system writes to create HTML debug pages.\n
- Sanitization: There is no indication of sanitization or validation performed on the retrieved text before it is processed by the agent.
Audit Metadata