prompt-skills
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests user-provided text and code snippets to generate structured outputs. \n
- Ingestion points: User input collected during Step 1 in SKILL.md (name, description, and script/reference content). \n
- Boundary markers: The output format uses standard Markdown structure but does not define specific adversarial delimiters for the interpolated content. \n
- Capability inventory: The skill only produces text output and does not have the ability to write files, access sensitive system paths, or initiate network connections. \n
- Sanitization: The instructions do not specify sanitization for the user-provided inputs before they are incorporated into the generated prompt. \n- [EXTERNAL_DOWNLOADS]: The skill metadata includes a reference to the author's official GitHub repository (github.com/marioluciofjr/skills). This is an informative link to the vendor's own resources and does not involve suspicious or unauthorized downloads.
Audit Metadata