The Agent Skills Directory

[SAFE]: The skill performs legitimate documentation tasks using local file access and does not exhibit any malicious behavior.
[COMMAND_EXECUTION]: The skill includes a local utility script (scripts/extract_api.js) used to parse Angular source code. The script uses safe regular expression matching and does not execute the code it reads.
[DATA_EXFILTRATION]: No network activity was detected. The skill only reads from and writes to the local project directory as part of its primary function.
[PROMPT_INJECTION]: The skill processes untrusted source code to generate documentation, which is a potential surface for indirect prompt injection. The risk is minimal as information is extracted via structured regex parsing.
Ingestion points: scripts/extract_api.js reads TypeScript source files.
Boundary markers: None explicitly used during prompt interpolation.
Capability inventory: Filesystem write access to create or update README.md.
Sanitization: Content is parsed using regular expressions to extract specific signatures rather than direct LLM summarization of entire files.

domain-readme