facebook-strategy
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to draft replies to user comments on social media, creating an indirect prompt injection surface. Malicious content within a comment could potentially override the agent's instructions or influence its generated responses.\n
- Ingestion points: Processes external user comments to generate reply copy (SKILL.md).\n
- Boundary markers: Lacks instructions for using delimiters or explicit warnings to ignore embedded commands within user content.\n
- Capability inventory: Capable of drafting social media posts, Reels scripts, and replies, and interacts with the WoopSocial scheduling tool (SKILL.md).\n
- Sanitization: No sanitization or filtering logic is defined for the external text being processed.\n- [NO_CODE]: The skill consists entirely of Markdown documentation and JSON configuration files. No executable scripts (e.g., Python, JavaScript, Shell) are included in the skill package.
Audit Metadata