team-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that can influence agent behavior.
- Ingestion points: The skill ingests data from external sources using
gh pr viewandgh pr diffinSKILL.md(Phase 0), which includes PR titles, bodies, and comments. - Boundary markers: While the prompt templates in
references/agent-catalog.mduse structured headers and checklists to define scope, they do not include explicit instructions or delimiters to ignore potentially malicious instructions embedded within the code diffs or PR comments. - Capability inventory: The orchestrator and sub-agents have access to sensitive tools including
Bash,WebFetch,TaskCreate, andSendMessageinSKILL.md. - Sanitization: There is no evidence of sanitization or filtering of the external content before it is interpolated into the prompts for the specialized reviewer agents.
Audit Metadata