kol-engager-icp
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted content from external sources.
- Ingestion points: The skill retrieves LinkedIn post text and user comments using Apify actors in
scripts/kol_engager_icp.py(e.g.,scrape_kol_postsandscrape_engagers). - Boundary markers: No delimiters or safety instructions are used when processing or exporting the scraped text.
- Capability inventory: The skill allows execution of Python scripts that perform network operations and file system writes.
- Sanitization: Scraped content, including user-generated comments, is stored and exported without sanitization or validation.
- [COMMAND_EXECUTION]: The skill operates by executing a local Python script (
scripts/kol_engager_icp.py) to orchestrate a multi-step data processing pipeline. This script manages API calls, data filtering, and file exports. - [DATA_EXFILTRATION]: The script performs network requests to
api.apify.comto fetch scraping results. This communication is authenticated using an API token and targets a well-known service, which is consistent with the skill's intended functionality.
Audit Metadata