security-assessment

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebases and local checklist files, which creates a vulnerability surface where malicious instructions embedded in the analyzed code could influence the agent's behavior.
  • Ingestion points: The skill processes user-provided repositories and relative file paths such as '../security-reviewer/checklists/'.
  • Boundary markers: No explicit delimiters or instructions are provided to the LLM to treat the analyzed codebase content as data rather than instructions.
  • Capability inventory: The skill is configured to use the 'run_security_assessment' MCP tool and standard system tools including Read, Grep, Glob, and Bash.
  • Sanitization: No sanitization or validation of the ingested code content is described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 03:59 AM
Security Audit — agent-trust-hub — security-assessment