executar-bugfix
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from project documentation files to drive its execution logic.
- Ingestion points:
SKILL.mdStep 1 instructs the agent to read and extract information from./tasks/prd-[feature-slug]/bugs.md,prd.md, andtechspec.mdto guide the fixing process. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the processed documentation are present.
- Capability inventory: The skill possesses the ability to execute local shell commands (
bun run test,bun run typecheck), perform web navigation and interaction (Playwright MCP), and modify local files (bugs.md). - Sanitization: There is no evidence of sanitization, filtering, or validation of the content read from these external files before the agent processes them as instructions for planning and implementation.
Audit Metadata