audience-growth-tracker-sms

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill. The logic is focused strictly on data analysis and reporting.
  • [DATA_EXFILTRATION]: The skill accesses a local context file (.agents/social-media-context-sms.md) to personalize its analysis. This information is used internally to improve report relevance and is not transmitted to any unauthorized external domains.
  • [COMMAND_EXECUTION]: The skill references specific tools for metric retrieval (e.g., get_follower_growth, get_metric_timeseries, list_posts). These tools are used for data ingestion and do not allow for the execution of arbitrary shell commands or system-level operations.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external follower data and user-provided tables, it lacks the exploitable capabilities (such as shell access, file-writing, or arbitrary network requests) that would make it vulnerable to high-risk indirect injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 11:19 AM