thermo-nuclear-review
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and take into account findings from PR/MR discussions using the
ghorglabCLI tools. - Ingestion points: Pull request and Merge request discussion comments (SKILL.md).
- Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore potentially malicious instructions embedded within those external comments.
- Capability inventory: The agent is authorized to use version control CLI tools (
gh,glab) and has read access to the local codebase. - Sanitization: Absent. There are no requirements for the agent to sanitize, escape, or validate the content retrieved from the discussion threads before processing it.
Audit Metadata