apify-job-boards

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes job postings from various external sites, creating an attack surface for indirect prompt injection. 1. Ingestion points: Data is fetched via 'apify datasets get-items' into the agent context (SKILL.md, Step 4). 2. Boundary markers: The skill lacks explicit delimiters or instructions to ignore commands within scraped text. 3. Capability inventory: The agent can execute CLI commands and network operations to interact with Actors and datasets. 4. Sanitization: No content filtering is described in the workflow.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to run remote code via Apify Actors 'flash_scraper/multi-jobboard-scraper' and 'flash_scraper/remote-job-aggregator'. These actors belong to a third-party namespace rather than the official vendor, constituting a dependency on unverifiable remote code.
  • [SAFE]: Interaction with the 'apify.com' domain and the Apify CLI are official vendor activities. Token management instructions prioritize secure environment variables and headers over hardcoding.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:19 PM
Security Audit — agent-trust-hub — apify-job-boards