prioritize-python-3-10-features
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
SKILL.mdfile defines a 'Memory Protocol' that requires the agent to execute the shell commandcat .claude/context/memory/learnings.md. While this is a common pattern for maintaining state in certain agentic environments, it involves direct interaction with the host filesystem via shell execution. - [PROMPT_INJECTION]: The skill uses forceful directives such as 'MANDATORY' and 'follow it exactly' within
SKILL.mdandcommands/prioritize-python-3-10-features.md. These are intended to ensure the agent adheres to specific coding standards but are characteristic of behavior-override patterns. - [DATA_EXPOSURE]: The mandatory instruction to read
.claude/context/memory/learnings.mdconstitutes an exposure of local context files. Although these files are typically managed by the agent itself, the capability to read local filesystem data is present. - [SAFE]: The provided Node.js script (
scripts/main.cjs) and execution hooks (pre-execute.cjs,post-execute.cjs) contain boilerplate code for argument parsing and metric recording with no malicious logic detected.
Audit Metadata