linkedin-hook-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to fetch and analyze external LinkedIn posts which are untrusted data sources.
- Ingestion points: External post content is ingested via
lib.ApifyClient.fetch_post(url)or user copy-paste inSKILL.md. - Boundary markers: The skill includes a dedicated 'Untrusted content' section in
SKILL.mdwith explicit instructions to treat fetched text as data only and to ignore instructions within it. - Capability inventory: The skill performs URL parsing, external API calls via Apify, and structured text analysis/template generation.
- Sanitization: While it contains logical 'don't follow instructions' rules for the LLM, it lacks technical sanitization or schema-based filtering of the raw text before analysis.
Audit Metadata