The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell scripts, phase1_discovery.sh and phase2_analysis.sh, to perform its core functions. These scripts utilize standard system utilities such as find, grep, wc, and git to inspect the project directory, analyze folder structures, and identify potential code quality or security issues like hardcoded credentials and SQL injection patterns.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill ingests untrusted data by reading the content of the project being analyzed, including source code files, package.json, README.md, and git history.
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing the content of the analyzed files.
Capability inventory: The agent has the capability to execute the analysis scripts and write multiple markdown reports to the docs/analyze/ directory.
Sanitization: There is no explicit sanitization or filtering mentioned for the data extracted from the analyzed files before it is used to populate report templates.
[DYNAMIC_EXECUTION]: The bash scripts use python3 -c to execute embedded, static Python one-liners for parsing JSON data from project files (e.g., package.json). This is a low-risk use of dynamic execution for localized data processing.

project-analyzer