apify-lead-generation
Fail
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- CREDENTIALS_UNSAFE (HIGH): The skill uses
grepandxargsto readAPIFY_TOKENfrom a.envfile, which is a sensitive credential store. - EXTERNAL_DOWNLOADS (MEDIUM): The skill instructs the user to install the
@apify/mcpcpackage globally, introducing an unverified external dependency. - COMMAND_EXECUTION (MEDIUM): The skill executes shell commands (
node,mcpc) with dynamic parameters likeACTOR_IDandJSON_INPUT, creating a risk for command injection. - PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection from scraped web data. Evidence: 1. Ingestion points: Scraped data from various platforms in Step 4 and 5. 2. Boundary markers: Absent. 3. Capability inventory: Shell execution (
node,mcpc). 4. Sanitization: Absent.
Recommendations
- AI detected serious security threats
Audit Metadata