social-content
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The 'Reverse Engineering' framework described in 'references/reverse-engineering.md' introduces a vulnerability to indirect prompt injection by processing large datasets of untrusted external content.
- Ingestion points: Data is brought into the agent's context via the scraping of social media posts (LinkedIn, Twitter, etc.) as detailed in the 'SCRAPE' step of the framework.
- Boundary markers: There are no explicit instructions or delimiters defined to separate the data being analyzed from the agent's core instructions, nor are there 'ignore embedded instructions' warnings.
- Capability inventory: The skill tasks the agent with analyzing patterns, extracting hooks, and generating content playbooks based on the untrusted data.
- Sanitization: The skill lacks any description of sanitization, filtering, or validation steps to neutralize potential malicious instructions within the scraped social media posts.
Audit Metadata