linkedin-post-research
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from LinkedIn posts, which serves as a potential surface for indirect prompt injection if the output is interpreted by an LLM without proper isolation.
- Ingestion points: Fetches external post content (text, author, and preview) via the Crustdata API in
scripts/search_posts.py. - Boundary markers: None. The output is written to JSON or CSV files without specific delimiters or instructions for downstream LLMs to ignore embedded content.
- Capability inventory: The skill possesses the ability to perform network requests (
requests.post) and write to the local file system (--output-file). - Sanitization: Basic text formatting (stripping newlines and truncating to 200 characters) is performed on post previews, but no specialized sanitization for prompt injection is present.
Audit Metadata