sast-hardcodedsecrets

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill scans codebase files, which are untrusted external inputs, creating a surface for indirect prompt injection where malicious instructions hidden in code could influence the agent's behavior during verification.
  • Ingestion points: The Recon phase scans the entire codebase (e.g., Phase 1 instructions to 'Scan the entire codebase').
  • Boundary markers: Absent. The instructions do not define specific delimiters or 'ignore' commands for the content being processed.
  • Capability inventory: File system write operations are performed to save results to the 'sast/' directory.
  • Sanitization: The skill implements a safety measure by requiring partial redaction of detected secrets (e.g., 'AKIA****EXAMPLE') in the final reports to prevent further credential exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:34 AM
Security Audit — agent-trust-hub — sast-hardcodedsecrets