social-rising-topic-radar-cn

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary functionality is to send user-provided content to a remote API (ai-skills.ai) for analysis. This behavior is clearly documented and consistent with the skill's stated purpose.
  • [SAFE]: The runner script scripts/run.py implements standard API communication patterns, including secure handling of the AISKILLS_API_KEY via environment variables.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to process untrusted external data (social media text, uploaded files, and links).
  • Ingestion points: Untrusted data enters the context via trendSignalText, trendSignalFile, and trendSourceLink fields defined in references/skill.json.
  • Boundary markers: No explicit delimiter or boundary instructions are present in the provided configuration files.
  • Capability inventory: The skill's local script is limited to performing network requests to the vendor's API and printing the result. It does not have file-writing or subprocess execution capabilities based on returned data.
  • Sanitization: There is no evidence of local sanitization or filtering of the ingested external content before it is transmitted to the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:31 AM
Security Audit — agent-trust-hub — social-rising-topic-radar-cn