pr-report
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that could contain malicious instructions designed to influence the agent's behavior or poison the generated output.
- Ingestion points: The agent is instructed to gather contributor intent from PR text, design documents, and external repository source code, specifications, and invariants (SKILL.md).
- Boundary markers: The instructions lack specific directives to use delimiters or implement "ignore embedded instructions" warnings for the ingested data.
- Capability inventory: The skill performs file read operations on local repository code and writes report artifacts as HTML or Markdown to the local filesystem (SKILL.md).
- Sanitization: There is no requirement in the instructions to sanitize or escape external content before it is interpolated into the HTML report starter template.
- [EXTERNAL_DOWNLOADS]: The HTML starter template included with the skill references external resources from well-known services.
- Evidence: The template fetches typography and font assets from Google Fonts via fonts.googleapis.com and fonts.gstatic.com (assets/html-report-starter.html).
Audit Metadata