agent-skills-framework
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The framework is installed and updated from a remote GitHub repository (
github.com/addyosmani/agent-skills.git). This is a standard distribution method for tools on the GitHub platform. - [INDIRECT_PROMPT_INJECTION]: The
source-driven-developmentworkflow processes content from external documentation URLs (e.g., redis.io, stripe.com). - Ingestion points: Documentation content fetched from external URLs during the
source-driven-developmentprocess, as seen in the SKILL.md file. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential directives within the fetched documentation.
- Capability inventory: The skill framework enables file manipulation, tool execution, and code implementation through various command workflows.
- Sanitization: No specific sanitization or filtering of the fetched content is described.
- [CREDENTIALS_UNSAFE]: The documentation includes an environment variables section with placeholders like
<your-redis-password>and<your-jwt-secret>. These are used appropriately as guidance for the user and do not contain actual secrets or hardcoded credentials.
Audit Metadata