The Agent Skills Directory

[SAFE]: The skill is a legitimate administrative tool for documentation management. Analysis of the included scripts (kb_health_auditor.py, orphan_detector.py, doc_debt_ranker.py) confirms they are limited to local file system reads and standard data processing using Python standard libraries. No evidence of malicious activity, persistence, or data exfiltration was found.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection due to its processing of external documentation files. * Ingestion points: scripts/kb_health_auditor.py reads markdown content and YAML frontmatter from user-provided directories; all scripts read JSON document inventories. * Boundary markers: None; the scripts do not implement specific delimiters to isolate file content from instructions. * Capability inventory: Restricted to local file reading and structured reporting; no capabilities for network access or shell execution of document content were identified. * Sanitization: None; input strings are parsed as raw text without sanitization for potential injection attacks.

knowledge-ops