to-prd-project
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests information from the current conversation and repository files to generate a PRD. This output is then consumed by other agents, creating a multi-step chain where malicious instructions in the source context could potentially influence downstream tasks.
- Ingestion points: Ingests conversation history and repository documentation (
CONTEXT.md,docs/adr/) as described in the process steps ofSKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined to separate the synthesized PRD content from potential instructions in the source text.
- Capability inventory: Performs issue creation using the
ghCLI tool. - Sanitization: There is no evidence of data sanitization or validation performed on the ingested content prior to publication.
- [COMMAND_EXECUTION]: The skill utilizes the
ghCLI to publish the generated PRD as an issue in themattpocock/course-video-managerrepository. This aligns with the skill's stated purpose of automating project management workflows.
Audit Metadata