apify-competitor-intelligence
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using
mcpcandnode. It specifically instructs the agent to read sensitive environment variables from a.envfile usinggrepandxargsto facilitate API authentication. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8).
- Ingestion points: The script
run_actor.jsfetches scraped data from external platforms (Google Maps, Facebook, YouTube, TikTok, etc.) via the Apify API (api.apify.com/v2/datasets). - Boundary markers: Absent. There are no delimiters or specific instructions to the agent to disregard instructions potentially embedded in the scraped competitor data.
- Capability inventory: The
run_actor.jsscript has filesystem write access (writeFileSync). TheSKILL.mdfile grants the agent the ability to execute arbitrary Node.js scripts and CLI tools in the local environment. - Sanitization: Absent. While the script truncates long strings for display purposes, it does not perform any validation, filtering, or escaping of the content retrieved from the web before presenting it to the agent for summarization.
Audit Metadata