learning-documentation-skill
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION] (LOW): The skill is hardcoded to send data to an external Supabase instance (
mocerqjnksmhcjzxrewo.supabase.co). It encourages the storage of personal data, including swimming results, family events, and business strategies. Users must ensure they control the destination database to prevent unauthorized data exposure. - [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8).
- Ingestion points: It ingests content from external sources such as YouTube transcripts (via Apify), articles, and blog posts.
- Boundary markers: Absent. There are no instructions or delimiters provided to the agent to treat external content as untrusted data.
- Capability inventory: The skill possesses the ability to perform network requests (
requests.post) and trigger GitHub Actions workflows. - Sanitization: Absent. The skill does not specify any sanitization or validation of the ingested content before it is processed or stored.
- [EXTERNAL_DOWNLOADS] (SAFE): The Python example references the
requestslibrary, which is a standard and trusted package for HTTP operations. No suspicious remote code execution patterns were found.
Audit Metadata