apify-lead-generation
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external sources (e.g., social media profiles, Google Maps, web pages) and presents it to the agent.
- Ingestion points: External data enters the agent context via the
displayQuickAnswerandreportSummaryfunctions inreference/scripts/run_actor.jswhich fetch and display lead information. - Boundary markers: Absent. The instructions in
SKILL.mddo not provide delimiters or warnings to the agent to ignore potential instructions embedded within the scraped lead data. - Capability inventory: The
run_actor.jsscript has capabilities to write files to the local filesystem (writeFileSync) and perform network requests (fetch). - Sanitization: The script performs basic CSV escaping and string truncation for display, but does not sanitize the content for malicious LLM instructions.
Audit Metadata