bmad-os-gh-triage
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): Detected potential for Indirect Prompt Injection.
- Ingestion points: Issue titles and bodies are fetched from GitHub via the
ghCLI as described inprompts/instructions.md. - Boundary markers: The prompt in
prompts/agent-prompt.mduses a simple placeholder[Paste the batch of issues here]without robust delimiters or 'ignore' instructions for the data section. - Capability inventory: The skill generates
ghCLI commands (close, comment, migrate) in its final report based on the AI's analysis of the untrusted data. - Sanitization: There is no evidence of sanitization or filtering of issue content before it is passed to the sub-agent for analysis.
- Command Execution (SAFE): The use of the
ghCLI for fetching and managing issues is consistent with the skill's primary stated purpose. There are no signs of arbitrary or malicious command execution.
Audit Metadata