linkedin-post-research
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes user-generated content from LinkedIn, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The script
scripts/search_posts.pyretrieves external data including author names, headlines, and full post text from the Apify dataset API. - Boundary markers: No explicit delimiters or boundary markers are used to isolate the fetched external content from the agent's instructions, nor are there warnings provided to the agent about the untrusted nature of the data.
- Capability inventory: The
search_posts.pyscript possesses network capabilities (accessing Apify and Gooseworks APIs) and file system capabilities (writing search results to a local file when using the--output-fileflag). - Sanitization: The script does not perform any sanitization, filtering, or escaping of the fetched text content before passing it back to the agent or user.
- [COMMAND_EXECUTION]: The skill is designed around a Python command-line utility (
scripts/search_posts.py) that performs network operations and local file writing based on user-supplied arguments.
Audit Metadata