self-media-trend-radar
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly limited to data analysis and research operations. It does not include any executable scripts, shell commands, or external software dependencies that could be used for malicious purposes.\n- [DATA_EXFILTRATION]: The skill includes clear security requirements in
references/research-safety.mdthat prohibit the storage or transmission of sensitive credentials (Cookies, Tokens, Secrets). It also mandates that all research be conducted using isolated accounts to prevent session hijacking or unauthorized access to user accounts.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze external data from social media platforms.\n - Ingestion points: Public links, competitor homepages, and search results (SKILL.md).\n
- Boundary markers: The instructions do not specify the use of delimiters or escaping mechanisms when interpolating external content into the model context.\n
- Capability inventory: The skill is restricted to information gathering and cannot perform high-risk actions such as shell command execution, file system writes, or automated interactions (references/research-safety.md).\n
- Sanitization: The safety guidelines require the removal of personally identifiable information (PII) from collected samples before they are processed by the agent.
Audit Metadata