aios-writing-social
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it integrates data from external markdown files and Supabase database logs into its context without sanitization or delimitation.
- Ingestion points: companies/claim-supply/brand.md, audiences.md, voice-and-tone.md, content-strategy.md, and Supabase tables content_log and publishing_queue.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present.
- Capability inventory: The skill is capable of generating structured social media content for multiple platforms.
- Sanitization: There is no evidence of filtering or escaping for the retrieved data.
Audit Metadata