test-strategy-author

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied feature scope and risk matrices to produce structured test plans, creating an attack surface where malicious data could influence agent output.
    • Ingestion points: External data sources include the feature scope and the risk matrix referenced in the Step 5 planning workflow.
    • Boundary markers: Absent; the instructions do not specify delimiters or protective framing to separate external input from the agent's core instructions.
    • Capability inventory: The skill is strictly instructional and document-focused; it does not contain code execution tools, network access, or file-writing scripts.
    • Sanitization: Absent; there is no logic provided to filter or validate the content of the ingested project data.
  • [NO_CODE]: The skill consists entirely of Markdown-based templates and configuration metadata, with no accompanying scripts, binaries, or executable logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 02:30 PM
Security Audit — agent-trust-hub — test-strategy-author