linkedin-company-pages
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill's instructions or referenced files. The code is purely instructional and focused on social media strategy.
- [PROMPT_INJECTION]: The skill ingests untrusted data from
brand-profileandgoals-and-kpis, which creates a theoretical surface for indirect prompt injection. However, the risk is negligible because the skill lacks the capabilities required to perform dangerous operations like shell execution or unauthorized network access. - Ingestion points: Contextual files
brand-profileandgoals-and-kpisreferenced inSKILL.md. - Boundary markers: None specified in the prompt instructions for isolating external data.
- Capability inventory: The skill is restricted to drafting text and performing structured social media publishing via the WoopSocial tool. No arbitrary code execution or file system access is present.
- Sanitization: No explicit content sanitization or validation logic is defined.
- [DATA_EXFILTRATION]: No evidence of unauthorized data exfiltration or hardcoded credentials. All tool usage is consistent with the skill's stated purpose of social media management.
Audit Metadata