The Agent Skills Directory

[SAFE]: No malicious patterns, executable code, or network-based threats were found. The skill is entirely instructional and serves as a formatting guide for documentation.
[NO_CODE]: This skill contains no scripts, binaries, or automated tools. It is composed entirely of markdown instructions, style guides, and templates.
[PROMPT_INJECTION]: Evaluated for indirect prompt injection risks as the skill processes external documentation. The risk is assessed as safe because the skill has no operational capabilities that could be exploited by malicious content within the processed documents.
Ingestion points: Technical documentation provided for condensation (referenced in SKILL.md)
Boundary markers: None identified in the instructional content
Capability inventory: No file system access, network requests, or code execution capabilities are defined or available
Sanitization: No sanitization or escaping logic is implemented as the output is purely informational text

doc-condenser