pain-language-engagers
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill integrates with the Apify platform, a well-known cloud service, to perform data collection. It executes specific scraping actors to search for LinkedIn posts and enrich profiles, communicating solely with the api.apify.com domain.
- [DATA_EXFILTRATION]: The script reads the APIFY_API_TOKEN from a local .env file, which is a secure practice for managing sensitive credentials. The data retrieved from LinkedIn is stored in local CSV files and is not exfiltrated to unauthorized third-party servers.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests LinkedIn content, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: Post text and user comments are retrieved via Apify actor datasets.
- Boundary markers: The skill does not use specific delimiters or warnings to isolate ingested content.
- Capability inventory: The script has the ability to perform network requests to Apify and write lead data to the local file system.
- Sanitization: External content is processed using regular expression keyword matching to identify relevance, rather than being passed into prompt templates for interpretation as instructions.
- [COMMAND_EXECUTION]: The skill provides a Python-based pipeline for automation. The command-line interface and script logic are well-defined, lacking patterns of unsafe command interpolation or dynamic shell execution.
Audit Metadata