The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze user-provided skill directories and SKILL.md files. This represents an indirect prompt injection surface where a malicious file could contain instructions designed to influence the AI's grading or suggestions.
Ingestion points: Path to a skill directory or SKILL.md file as specified in the Inputs section of SKILL.md.
Boundary markers: Absent; the skill does not specify delimiters or warnings to isolate the content of the skill being analyzed from the agent's instructions.
Capability inventory: Executes a local bash script for linting; generates a prioritized report of improvements; may modify files if the user requests application of changes.
Sanitization: Absent; the skill reads and processes the text of the provided files directly.
[COMMAND_EXECUTION]: The skill executes a bundled shell script (scripts/skill-lint.sh) to automate mechanical checks like frontmatter validation and file size checks. While the script is read-only and uses safe quoting for variables, it represents an automated command execution path within the skill's workflow.

skill-improver