social-content
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework involves analyzing large volumes of external, untrusted social media content (posts, hooks, and formats) as part of its 'Reverse Engineering' strategy. This creates an ingestion surface where instructions hidden within analyzed content could potentially influence agent behavior.
- Ingestion points: External social media posts gathered for analysis as described in
references/reverse-engineering.md. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the data being analyzed.
- Capability inventory: The skill defines no scripts, tool invocations, or sensitive operations (e.g., file writing, network requests) across its instructions.
- Sanitization: No sanitization or validation of external content is implemented.
- [NO_CODE]: The skill consists entirely of Markdown instructions, strategy guides, and content templates. It does not include any Python or Node.js scripts, shell commands, or configurations for external tool execution.
Audit Metadata