skill-health-check
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were found in the skill files or scripts.
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute a local Node.js script (scripts/skill-lint.js) which performs the health check logic. This is a legitimate use of the tool for the skill's primary function. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external skill and command files. Ingestion points: Files in the
skills/andcommands/directories are read byscripts/skill-lint.js. Boundary markers: The output is formatted as a Markdown report without additional isolation delimiters for external content. Capability inventory: The skill has access toBash,Read,Grep, andGlobtools. Sanitization: No content sanitization is performed on the audited files before inclusion in the health report. This surface is expected for an audit tool and does not escalate the verdict.
Audit Metadata