evo-writing-plans
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted user specifications to generate implementation plans containing executable code and shell commands.
- Ingestion points: User-provided specifications or requirements for multi-step tasks.
- Boundary markers: Absent. The skill does not employ delimiters or specific instructions to prevent the agent from obeying malicious instructions embedded within the user requirements.
- Capability inventory: The generated output includes Python code and shell commands (e.g.,
git,pytest) intended to be executed by the user or a downstream skill (e.g.,evo-executing-plans). - Sanitization: Absent. Input requirements are directly interpolated into the structured markdown tasks without validation or escaping.
- [COMMAND_EXECUTION]: The skill templates and encourages the generation of shell commands for version control and testing operations.
- Evidence: The plan structure includes specific commands such as
git add,git commit, andpytestwith paths and parameters derived from the generated plan content.
Audit Metadata