platform-request
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local command-line tools including
git,gh, andnodeto collect technical environment metadata, manage branches, and submit issues to GitHub. These operations are restricted to the local repository context and the official project issue tracker. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user interviews to populate external issue templates, creating a potential surface for prompt injection.
- Ingestion points: User responses provided during the interview phase in
SKILL.md(Step 1). - Boundary markers: The skill employs a structured template (
issue-template.md) and mandates a final review of the draft by the user before the issue is submitted. - Capability inventory: Access to
gh issue create,git push, and execution of a local scriptnode scripts/mock-shot.mjs. - Sanitization: The instructions explicitly direct the agent to anonymize and remove all personally identifiable information (PII)—including names, dates, and identifiers—before processing the data for inclusion in the issue.
Audit Metadata