The Agent Skills Directory

[COMMAND_EXECUTION]: The SKILL.md file contains instructions for the agent to execute shell commands (python3 scripts/evaluate.py and python3 scripts/optimize.py) that pass user-supplied strings directly as command-line arguments.
[NO_CODE]: The skill references specific script files (scripts/evaluate.py, scripts/optimize.py) to perform its primary functions, but these files were not included in the analysis package, making the actual logic unverifiable.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design.
- Ingestion points: User-provided prompts are ingested via command-line arguments as seen in SKILL.md.
- Boundary markers: No explicit boundary markers or delimiters are defined in the instructions to isolate user input from the command execution.
- Capability inventory: The skill uses python3 to execute scripts that process user-provided data.
- Sanitization: Specific sanitization or validation logic is not visible as the referenced scripts are missing.

prompt-optimizer