The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool as a fallback mechanism to locate method boundaries using grep. While this is a powerful tool, its use is restricted to local text processing as part of the primary analysis logic.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted source code as its primary input. Malicious instructions embedded within the analyzed code (e.g., in comments) could theoretically attempt to influence the agent.
Ingestion points: Source code is ingested through the Read and mcp__serena__find_symbol tools during the 'Read Target Code' phase.
Boundary markers: The skill does not define specific delimiters or 'ignore' instructions when passing the read source code to the LLM for analysis.
Capability inventory: The agent possesses the Bash, Write, Read, Grep, and Glob tools, along with specialized symbol searching tools.
Sanitization: No explicit sanitization or validation of the input source code is performed prior to the analysis and flowchart generation steps.

re-visualize-logic