b2c-organic-social-media-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides educational content and growth marketing strategies. No malicious code, obfuscation, or unauthorized access patterns were detected.
- [EXTERNAL_DOWNLOADS]: The skill suggests installing a companion tool via the command
npx skills add post-bridge-hq/agent-mode. This resource originates from the skill's author ('post-bridge-hq') and follows standard extension patterns for related services. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding their products and performance metrics to provide coaching. While this represents a data ingestion surface, the lack of high-privilege capabilities within the skill and the context of its use-case make this surface acceptable.
- Ingestion points: User-provided product descriptions and performance data (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The instructions recommend a companion skill which interacts with the 'Post Bridge' API and CLI for media management.
- Sanitization: No specific input sanitization steps are documented.
Audit Metadata