alterlab-akademik-tesvik
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of instructions and code confirmed no malicious patterns, credentials, or data exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill handles user data with an ingestion point for academic activities. It uses structural boundaries (JSON) and requires a Python script to validate input keys against a strict whitelist, mitigating injection risks. Ingestion point: user activities. Boundary markers: JSON structure instructions. Capabilities: local script execution. Sanitization: whitelist validation in code.
- [METADATA_POISONING]: The frontmatter contains a future date in the last_updated field, which appears to be a clerical error and poses no risk.
- [COMMAND_EXECUTION]: The skill executes a local Python script using the uv tool. This process is confined to the skill's subdirectory and does not allow for dynamic shell injection or remote code execution.
Audit Metadata