improve-ocp
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform a
git logcheck to identify 'shotgun surgery' evidence by analyzing which files are frequently changed together in the repository history (SKILL.md, Step 1, Signal 5). This involves executing a shell command on the local system.\n- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection (Category 8) because it is designed to ingest and process arbitrary data from a codebase.\n - Ingestion points: The skill uses an Agent tool with
subagent_type=Exploreto sweep the entire codebase and reads specific confirmed files (SKILL.md, Step 1).\n - Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the analyzed source files.\n
- Capability inventory: The skill has the capability to write a new file (
IMPROVE-OCP.md) to the project root based on the data it has ingested.\n - Sanitization: There is no logic provided to sanitize or filter external content extracted from the codebase before it is used to generate the final report.
Audit Metadata