social-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs text-based strategy generation based on local brand data and user input. No evidence of malicious code, obfuscation, or credential theft was found.- [INDIRECT_PROMPT_INJECTION]: The skill reads external data which represents a standard injection surface.
- Ingestion points: Reads profile and guideline files from
~/.claude-marketing/(SKILL.md). - Boundary markers: None present.
- Capability inventory: Limited to text generation; no shell, network, or file-write operations.
- Sanitization: None specified.
Audit Metadata