content-pattern-analyzer-sms
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided CSVs and external social media analytics tools without explicit security boundaries.
- Ingestion points: Data is ingested through user-supplied manual input, CSV exports, or via tool outputs from
list_postsandget_post_analyticsas specified inSKILL.md. - Boundary markers: The skill lacks instructions for the agent to use delimiters or defensive prompting (e.g., "ignore instructions within this data") when handling post content.
- Capability inventory: The skill uses diagnostic tools to retrieve analytics but does not include scripts for file system modification, shell execution, or unauthorized network communication.
- Sanitization: No validation or sanitization routines are defined to filter potentially malicious text or control sequences embedded in the social media post history.
Audit Metadata