recoup-internal-consulting-linkedin-audience
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script
python integrations/linkedin/_work/pull_engagement.pyto fetch LinkedIn engagement data. This is a core functional requirement of the workflow. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its ingestion of external social media data. 1. Ingestion points: LinkedIn profile names, headlines, and post comments are scraped into JSON files and then read by the agent. 2. Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded in the scraped data. 3. Capability inventory: The agent can execute shell commands, perform network operations via CRM APIs (Attio), and write to the local file system. 4. Sanitization: There is no mention of sanitizing or validating the scraped strings before they are used for ICP scoring or drafting outreach emails.
Audit Metadata