pythia-review

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of a command-line utility named pythia. It invokes several subcommands including pythia errors, pythia src, pythia impact, and pythia similar to perform database analysis and retrieve source code.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests and processes untrusted data in the form of PL/SQL source code.
  • Ingestion points: Source code is read into the agent's context using the pythia src NAME command (SKILL.md).
  • Boundary markers: The instructions do not define explicit delimiters or warnings to prevent the agent from interpreting instructions contained within the analyzed code (e.g., inside SQL comments).
  • Capability inventory: The agent uses the pythia CLI tool to fetch data and report findings. It does not demonstrate file-writing or network exfiltration capabilities in the provided scripts.
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved source code before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 04:12 AM
Security Audit — agent-trust-hub — pythia-review