story-pr-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as repository instructions, specifications, task lists, and transcripts.
- Ingestion points: Processes repo instructions, specs, task lists, status documents, and relevant transcripts in
SKILL.md(Section 1). - Boundary markers: The skill contains instructions to prioritize authority gates and inspected evidence over instructions from users or agents to ignore failures.
- Capability inventory: Manages worktrees, branches, PRs, and coordinates other agent tasks.
- Sanitization: No explicit sanitization or strict schema validation is mentioned for the ingested data.
Audit Metadata