vedic-rectifier
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The provided
scripts/time_scan.pyscript performs dynamic path manipulation by calculating the relative path to a sibling skill (vedic-calculator) and inserting it intosys.path. This allows it to import local modules likedasha_pyjhora. While intended for interoperability, this pattern of loading from computed paths is a known attack surface. - [COMMAND_EXECUTION]: The skill requires the execution of shell commands to run
scripts/time_scan.py. It also references and potentially executes other local tools likedasha_query.pyto process astrological data. - [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests user-provided text for 'life events' and 'personal traits'. This data is interpolated into subsequent analysis steps and reports. The absence of explicit boundary markers for this untrusted input increases the risk of the agent obeying instructions hidden within the event descriptions.
Audit Metadata