project-research

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it is designed to ingest and analyze external documentation and project source code. \n
  • Ingestion points: Reads local project files (code, configurations) and external official documentation or source code as defined in SKILL.md. \n
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the investigated materials. \n
  • Capability inventory: The skill can read local project files and execute read-only checks or verification tests. \n
  • Sanitization: No specific content validation or sanitization logic is described for the information retrieved from external sources. \n- [COMMAND_EXECUTION]: The skill's instructions allow the agent to perform read-only checks or execute verification runs on the local project code to substantiate research findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 05:10 PM
Security Audit — agent-trust-hub — project-research