linkedin-message-writer
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
curlcommands to interact with the Apify API for lead research and data retrieval. These operations are explicitly documented and target a well-known service (apify.com). \n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it retrieves and processes untrusted data from external sources. \n - Ingestion points: LinkedIn profile data and public post content are fetched via Apify's API (Phase 2, SKILL.md). \n
- Boundary markers: No delimiters or 'ignore embedded instructions' warnings are identified in the workflow for processing external content. \n
- Capability inventory: The agent can perform network requests via
curland write data to the local filesystem in CSV format (SKILL.md). \n - Sanitization: There is no mention of sanitizing or validating the retrieved LinkedIn post content before it is used to generate personalized messages.
Audit Metadata