The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructions require the agent to read local source code files to trace implementation paths and cite specific line numbers for documentation accuracy. This is a core function of the skill and does not include any instructions to transmit this data to external or untrusted domains.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it is designed to read and process local code files.
Ingestion points: The 'Analyze' procedure in SKILL.md specifies reading relevant files to identify patterns and data flow.
Boundary markers: There are no explicit boundary markers or 'ignore' instructions for the data being processed.
Capability inventory: The skill's documented output is limited to generating structured Markdown and Mermaid diagrams; it does not contain instructions for subprocess execution, file writing, or network operations.
Sanitization: No specific sanitization or validation of the ingested code content is mentioned.
Risk Assessment: Given that the skill only produces documentation text and lacks exploitable capabilities, the risk of indirect prompt injection is minimal.

wiki-page-writer