code-review
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from
git diffoutputs and external issue trackers, which are then passed to sub-agents for analysis. - Ingestion points:
SKILL.mddescribes fetching issue references and reading repository diffs which contain external, potentially attacker-controlled content. - Boundary markers: Absent. The instructions do not define clear delimiters or warnings to sub-agents to ignore instructions embedded within the diffs or specs.
- Capability inventory: The skill can spawn sub-agents (
runs.run), execute shell commands (git), and read arbitrary repository files. - Sanitization: Absent. Content is interpolated directly into prompts for sub-agents without escaping or validation.
Audit Metadata