Agent Development
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill consists of educational content, templates, and reference guides for agent development. It contains no malicious payloads, prompt injections, or unauthorized data access mechanisms.\n- [INDIRECT_PROMPT_INJECTION]: The agent templates (e.g.,
code-reviewer.md,test-generator.md) are designed to ingest external source code via tools likeReadandGlob. While this creates an inherent surface for indirect prompt injection, the skill is a development guide and the templates utilize structural markdown headers to organize output. No evidence of malicious exploitation was found.\n- [COMMAND_EXECUTION]: The skill includes a local utility scriptscripts/validate-agent.shfor validating metadata. This script uses standard Unix text-processing tools to parse frontmatter and does not perform network operations or execute commands from untrusted sources.
Audit Metadata