paw-ps-discovery
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from local configuration and shared memory files, creating a potential surface for indirect prompt injection. • Ingestion points: Reads from config.yaml, index.md, and daily log files. • Boundary markers: Absent; no specific delimiters or ignore-instructions are used for external data. • Capability inventory: Restricted to local file system reads and writes; no tools for network operations or command execution are provided. • Sanitization: Absent; the skill does not validate or sanitize the ingested content.
- [NO_CODE]: This skill package does not include any executable scripts or binary files, consisting entirely of Markdown instructions and documentation.
Audit Metadata