claude-project-manifest

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is documentation-based and does not provide any executable code or request any tool permissions. It focuses on project organization and knowledge mapping through YAML and JSON templates.
  • [SAFE]: The guidelines in 'references/annotation-guidelines.md' and the manifest templates explicitly include security warnings, advising users to use environment variables for secrets instead of storing them within manifest files.
  • [SAFE]: Python code snippets provided as workflow integration examples in 'references/workflow-integration.md' demonstrate secure practices, such as using 'yaml.safe_load()' to avoid vulnerabilities associated with untrusted data deserialization.
  • [NO_CODE]: The skill folder contains only markdown documentation, YAML/JSON schemas, and template files. No functional scripts or binaries are distributed with the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 03:25 AM