social-analytics
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external social media profiles (Twitter, Instagram, LinkedIn) which is inherently untrusted and could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: Social media profile data, posts, and engagement metrics fetched via 'requests', 'beautifulsoup4', 'tweepy', and 'instaloader' (SKILL.md).\n
- Boundary markers: Absent; the instructions do not specify any delimiters or guidelines to treat the external fetched content as data only.\n
- Capability inventory: The skill executes a local script ('scripts/main.py') to process this data, creating a potential path for manipulated content to influence generated reports or metrics.\n
- Sanitization: Absent; there is no mention of filtering or validating the external content before processing.\n- [COMMAND_EXECUTION]: The skill uses shell-based command execution via the Python interpreter to run its core scripts ('scripts/main.py'). While standard for skill operation, this provides the mechanism for interacting with the file system and network based on the provided instructions.
Audit Metadata