apify-audience-analysis
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external social media platforms (Facebook, Instagram, YouTube, TikTok) via Apify Actors.
- Ingestion points:
reference/scripts/run_actor.jsdownloads dataset items and actor schemas from the Apify API. - Boundary markers: No delimiters or instructions to ignore embedded commands are present when processing the external data.
- Capability inventory: The skill utilizes shell command execution in
SKILL.md(viamcpcandnode) and file-writing capabilities inreference/scripts/run_actor.js(writeFileSync). - Sanitization: No sanitization or validation of the retrieved content is performed before it is displayed to the user or saved to disk.
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the
@apify/mcpcCLI tool from the NPM registry. This is an official tool provided by Apify, which is a well-known service in the automation and scraping industry. - [COMMAND_EXECUTION]: The workflow involves executing shell commands to interact with the Apify platform, including fetching actor details and running a local JavaScript wrapper to execute remote actors.
Audit Metadata