product-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to perform a 'Codebase Audit' by searching through the user's local source code for SDK imports and tracking calls. This ingestion of untrusted external data (the user's codebase) creates a surface where malicious instructions embedded in code comments or strings could influence the agent's behavior.
- Ingestion points: The agent is directed to search and read local project files (SKILL.md, 'Codebase Audit' section).
- Boundary markers: None identified; the instructions do not specify delimiters to separate code content from agent instructions.
- Capability inventory: The skill utilizes file system searching and reading capabilities to extract event names and configuration details.
- Sanitization: No specific sanitization or filtering of the ingested codebase content is mentioned.
- [DATA_EXPOSURE]: The instructions direct the agent to 'Find tracking initialization' and 'check if properly configured with API keys'. This requires the agent to locate and process sensitive configuration data or environment variables related to analytics providers.
- [EXTERNAL_DOWNLOADS]: The skill recommends that users install an additional tool, 'skene-skills', from the vendor's official GitHub repository (github.com/SkeneTechnologies/skene-skills). As this targets a resource owned by the skill's author, it represents expected vendor functionality.
Audit Metadata