to-prd
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it ingests untrusted data from the conversation history and the codebase to generate and submit a GitHub issue.
- Ingestion points: Conversation context and codebase state (referenced in SKILL.md process).
- Boundary markers: None present; the skill does not use delimiters or instructions to ignore embedded commands in the source material.
- Capability inventory: Writing to external services (GitHub issues).
- Sanitization: No evidence of sanitization or validation of the synthesized content before submission.
Audit Metadata