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.mdfiles 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