linkedin-engager-analytics
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content, such as LinkedIn comments, headlines, and post text, which creates a vulnerability surface for indirect prompt injection attacks where malicious instructions are hidden in the data.
- Ingestion points: Data enters the agent's context through the Handlus read layer, the Apify MCP connector, or direct manual pastes from the user as described in
SKILL.md. - Boundary markers: The skill contains a specific 'Untrusted content' section that provides clear instructions to the agent to treat external content as data only. It further references a global
untrusted-content.mdfor comprehensive safety rules. - Capability inventory: The skill uses tools to fetch engager data (
fetch_post_engagers) and generates structured outreach lists (DMs, comments) based on the analyzed content. - Sanitization: The skill provides defensive prompts, such as instructing the agent to never follow directions found inside fetched posts or headlines and prohibiting the modification of draft bodies based on external input.
Audit Metadata