compare-audits

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and performing semantic analysis on external audit report files.
  • Ingestion points: The skill reads audit-report.md files from the local filesystem path ${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/security-auditor/data/machines/<machine_name>/reports/.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat the content of the audit reports as untrusted data.
  • Capability inventory: The skill uses shell commands (ls, head) to locate files and has the capability to read these files and write new markdown documents (-diff.md) to the filesystem.
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content of the audit reports before they are parsed and analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:15 PM
Security Audit — agent-trust-hub — compare-audits