shaman-tesla
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of persona instructions and structural frameworks (Five-Step Method, Seven-Item Checklist) in markdown format. It does not contain any scripts, binary files, or network-enabled tools.
- [PROMPT_INJECTION]: The skill incorporates external data through the
{{task}}placeholder and instructions to analyze 'failure signals' or 'original materials'. While this presents an indirect prompt injection surface, it is considered safe due to the complete absence of dangerous capabilities (such as code execution, file writing, or external network requests) that could be exploited. - Ingestion points:
{{task}}variable inSKILL.mdand checklist items for analyzing external materials inSKILL.v2.md. - Boundary markers: Absent; the skill relies on standard template interpolation.
- Capability inventory: None detected; no subprocess calls, network requests, or file system modifications are present in the provided files.
- Sanitization: Absent; the skill does not define methods for sanitizing user input.
Audit Metadata