sdd-review

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted artifacts (SPEC.md, TASK-PLAN.md, implementation code, and VERIFICATION.md) which could contain malicious instructions intended to subvert the review process or influence downstream agents.
  • Ingestion points: Untrusted data enters the agent context through the files specified for review in the 'Trigger Conditions' section of SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or 'ignore' instructions to isolate the content of reviewed artifacts from the agent's operational instructions.
  • Capability inventory: The skill's primary capabilities involve processing text and generating reports; no high-risk tools for network communication or system modification are requested.
  • Sanitization: There is no evidence of filtering, escaping, or validation logic to mitigate instructions embedded within the processed artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:03 PM
Security Audit — agent-trust-hub — sdd-review