quality-engineering

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or direct prompt injection attempts were detected in the skill instructions or associated reference files.
  • [SAFE]: The skill operates exclusively on project documentation and generates markdown artifacts. It does not perform network operations, access sensitive credentials (like .env or .ssh files), or execute shell commands.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from project documents such as PRDs and system designs.
  • Ingestion points: SKILL.md (Step 1) loads system-design.md, architecture documents, published contracts, and PRDs.
  • Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or ignore instructions within the ingested files.
  • Capability inventory: The skill is limited to documentation generation; it does not contain subprocess calls, network operations, or file-system writing capabilities beyond creating the testing strategy markdown.
  • Sanitization: No sanitization or validation of input content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 08:35 AM
Security Audit — agent-trust-hub — quality-engineering