social-content
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill instructs the agent to read '.claude/product-marketing-context.md' for context. While this is an ingestion point for untrusted data, the skill lacks any capabilities (network, file-write, or shell execution) that could be exploited via injection. \n- Ingestion points: .claude/product-marketing-context.md \n- Boundary markers: Absent \n- Capability inventory: None (text generation only) \n- Sanitization: Absent\n- General Security (SAFE): No malicious patterns, obfuscation, or hardcoded credentials were detected. The skill uses standard markdown and relative file references for documentation.
Audit Metadata