kol-content-monitor

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion and processing of untrusted content from LinkedIn and Twitter.
  • Ingestion points: External data enters the agent context via social media post scrapers (scrape_linkedin_posts.py and search_twitter.py).
  • Boundary markers: The instructions do not define delimiters or specific boundary markers to separate the untrusted scraped text from the agent's internal analysis logic.
  • Capability inventory: The skill has the capability to execute shell commands (running Python scripts) and write to the local file system (clients/<client-name>/intelligence/).
  • Sanitization: There is no mention of sanitizing or filtering the scraped content for embedded instructions before it is used for topic clustering or generating content recommendations.
  • [COMMAND_EXECUTION]: The skill relies on executing external Python scripts provided by the linkedin-profile-post-scraper and twitter-scraper skills. While these are documented dependencies, the safety of the kol-content-monitor skill depends on the integrity and security of these upstream scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM