The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/analyze.py uses the subprocess module to execute git commands such as git log, git ls-files, and git rev-parse. These operations are used to gather repository statistics and are limited to the provided directory path.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted data from the git repository.
Ingestion points: scripts/analyze.py extracts commit subjects, author names, and emails using git log.
Boundary markers: Absent. The skill instructions do not provide delimiters or warnings to the agent to ignore instructions embedded within the git metadata.
Capability inventory: The agent can write markdown files to the repository root and display formatted text to the user.
Sanitization: Absent. The data extracted from git is passed directly into the AI's context to generate the developer card.

dev-card