The Agent Skills Directory

[COMMAND_EXECUTION]: The skill contains an automated workflow that generates a shell script (analyze_skills.sh) at runtime, applies execution permissions, and runs it to perform dependency and pattern analysis.
[CREDENTIALS_UNSAFE]: The tool is instructed to read the .git/config file. This is a sensitive file path that often contains authentication tokens, private repository URLs, or other developer credentials.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted data from the project being analyzed (e.g., source code, dependency manifests).
Ingestion points: The skill uses cat and grep on files like requirements.txt, package.json, and various configuration files.
Boundary markers: There are no explicit instructions or delimiters used to prevent the AI from interpreting instructions contained within these files.
Capability inventory: The skill has the ability to execute shell commands and write files to the local system.
Sanitization: No sanitization or validation is performed on the content of the analyzed files before they are incorporated into the agent's context.

skill-analyzer