write-prd
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external repository sources which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill processes external content including repository context, code files, product decisions, issue trackers, and pull requests (found in Workflow steps 1 and 2 of
SKILL.md). - Boundary markers: Absent. The instructions do not define delimiters or provide warnings for the agent to ignore instructions embedded within the external data it reads.
- Capability inventory: The skill possesses capabilities to read local files, search repository issues/PRs, write to requirements documents, update issue bodies, and delegate tasks to other sibling skills (
SKILL.md). - Sanitization: Absent. There is no requirement for the agent to sanitize or escape content retrieved from the repository before it is interpolated into new documents or processed in subsequent steps.
Audit Metadata