skill-validator
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or obfuscation were detected. The skill provides clear guidance on best practices and security considerations, such as avoiding hardcoded secrets.
- [NO_CODE]: The skill consists entirely of markdown documentation and reference files. It does not ship with any executable scripts, binaries, or automated tools, which eliminates common technical attack vectors.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading and analyzing external skill files (SKILL.md and reference files), which constitutes a data ingestion surface. * Ingestion points: Phase 1 involves reading the target skill's SKILL.md and all reference files. * Boundary markers: No explicit instructions for delimiters or escaping untrusted data are provided. * Capability inventory: The skill is limited to analytical and reporting tasks; no subprocess execution, file-writing, or network exfiltration capabilities are present. * Sanitization: No specific input sanitization steps are documented.
Audit Metadata