linkedin-message-writer

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from the Apify API (api.apify.com) to research LinkedIn profiles and posts. Apify is a well-known service for web scraping and data extraction.
  • [COMMAND_EXECUTION]: The skill employs shell commands (curl) to interact with Apify actors, allowing the agent to programmatically trigger research tasks and retrieve results.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external content from LinkedIn to generate outreach messages.
  • Ingestion points: Profile data (headlines, history) and recent post content retrieved via the Apify API in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" markers when the agent interpolates research data into message templates.
  • Capability inventory: The skill possesses network access via curl and the ability to write files to the local workspace.
  • Sanitization: No sanitization, validation, or filtering is performed on the scraped content before it is presented to the agent for message generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 06:17 AM
Security Audit — agent-trust-hub — linkedin-message-writer