codekb-extract

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as source code comments, git history, and pull request descriptions which could contain malicious instructions designed to influence the extraction LLM.\n
  • Ingestion points: Ingests code content and git metadata through the codekb CLI tool across various scopes like src/payment.\n
  • Boundary markers: No specific delimiters or "ignore previous instructions" guards are defined to separate the code content from the extraction prompts.\n
  • Capability inventory: Triggers execution of the local codekb CLI tool; no direct file-write or network-exfiltration capabilities are explicitly requested in the skill manifest.\n
  • Sanitization: Employs a confidence-based review system where extractions with confidence < 0.7 are flagged for human review, providing a degree of protection against adversarial inputs.\n- [NO_CODE]: The skill consists solely of a markdown instruction file and does not include any accompanying scripts or executables.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 03:54 AM
Security Audit — agent-trust-hub — codekb-extract