detect-completed

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests user-supplied content from feature requests and performs analysis on it in Step 4 to determine if a feature has been shipped. An attacker could craft a feature request containing instructions that override the agent's logic.
  • Ingestion points: The skill fetches feature request titles and descriptions via the wccom-feature-requests-list tool as described in Step 3 of SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided skill instructions for the reasoning pass in Step 4.
  • Capability inventory: The skill has write capabilities, including posting comments via wccom-feature-requests-comment and updating request statuses via wccom-feature-requests-update-status.
  • Sanitization: The skill lacks sanitization or validation of the fetched description text before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 03:47 AM
Security Audit — agent-trust-hub — detect-completed