The Agent Skills Directory

[COMMAND_EXECUTION]: Executes local shell commands to audit repository state, verify markdown links, and perform version control operations. Evidence: Employs git diff, git log, wc -c, and a shell pipeline containing grep and sed to identify changed files and validate documentation integrity.
[PROMPT_INJECTION]: Contains an indirect prompt injection surface where malicious content in processed files could influence agent behavior. Evidence: The skill instructs the agent to read and summarize content from the repository and use it to generate updates. (1) Ingestion points: Reads untrusted data from *.md files, .env.example, and output from git commands. (2) Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded directives within the ingested files. (3) Capability inventory: The agent has the capability to write to the filesystem and execute git commit. (4) Sanitization: Absent; no validation or escaping of ingested content is performed before it is used in documentation tasks.

update-docs