kol-content-monitor
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guidelines or override core agent behaviors.
- [DATA_EXFILTRATION]: The skill does not access sensitive system files or credentials. It operates on publicly available social media profile data provided by the user.
- [REMOTE_CODE_EXECUTION]: While the skill invokes Python scripts, these are local components of the required sub-skills (linkedin-profile-post-scraper and twitter-mention-tracker) and do not involve downloading or executing untrusted remote code.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from LinkedIn and Twitter/X. While this represents a data ingestion surface common to monitoring tools, the skill uses markdown blockquote delimiters in its output to separate external content from analysis, which helps maintain context boundaries.
Audit Metadata