post-engagers
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches data from external LinkedIn scraping services including Apify, Phantombuster, and various providers on RapidAPI.
- [COMMAND_EXECUTION]: Utilizes the Anysite MCP tool to perform automated LinkedIn scraping operations.
- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection as it ingests and processes untrusted content (comments and headlines) from LinkedIn profiles.
- Ingestion points: LinkedIn post comments, reactions, and user profile headlines fetched from external scraping providers (SKILL.md).
- Boundary markers: Missing explicit delimiters or instructions to ignore embedded commands within the scraped text.
- Capability inventory: Ability to write data to local CSV files and perform network operations via the extruct-api skill (SKILL.md).
- Sanitization: No evidence of automated sanitization, escaping, or validation of the scraped text before it is processed for classification or displayed to the agent.
Audit Metadata