verify-work
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a structured framework for project verification tasks. No malicious patterns, obfuscation, or unauthorized data access detected.
- [PROMPT_INJECTION]: The skill ingests untrusted external data (tickets, PRDs, implementation plans) in Step 1. This represents an indirect prompt injection surface. Because the skill instructs the agent to run automated checks (Playwright/Appium) and update documentation, malicious content within a ticket could theoretically attempt to influence these actions.
- Ingestion points: PRD, ticket, implementation plan, or release note (Step 1).
- Boundary markers: None explicitly defined in the instructions for handling the external data.
- Capability inventory: Execution of automated checks (Playwright, Appium) and local command execution (traceability-audit) (Step 3 and Step 5).
- Sanitization: None specified for the ingested external data.
Audit Metadata