social-media-context-sms

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill reads and writes a configuration file at .agents/social-media-context-sms.md. This is used as a local persistent storage mechanism to maintain state and share context between different social media skills within the same environment.
  • [DATA_EXFILTRATION]: No network activity or external data transmission was detected. The skill collects identity and profile information, but it is stored locally. There are no calls to non-whitelisted domains or unexpected APIs.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a data ingestion surface as it reads the contents of .agents/social-media-context-sms.md to provide summaries and updates.
  • Ingestion points: Reads from .agents/social-media-context-sms.md in Step 1.
  • Boundary markers: The instructions do not specify explicit boundary markers (like XML tags) to wrap the file content, though the file itself uses Markdown headers.
  • Capability inventory: Limited to file read and write operations.
  • Sanitization: No specific sanitization or filtering of the ingested file content is mentioned. However, since the primary use is for summarization and editing, the risk is minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 11:19 AM