apify-brand-reputation-monitoring
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data scraped from external social media and review platforms.
- Ingestion points: Untrusted content is fetched from platforms like Google Maps, Facebook, Instagram, and TikTok via the Apify API in
reference/scripts/run_actor.js. - Boundary markers: The instructions in
SKILL.mdlack explicit delimiters or warnings to the agent to ignore any potential instructions embedded within the scraped data. - Capability inventory: The skill has the ability to write to the local file system using
node:fs.writeFileSyncinreference/scripts/run_actor.jsand is instructed to summarize the ingested data for the user. - Sanitization: There is no evidence of sanitization or filtering to detect or remove malicious instructions from the external content before it is presented to the agent.
Audit Metadata