skills/sahin/claude-skills/board-deck/Gen Agent Trust Hub

board-deck

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate automated reporting functions by reading data from specified local directories and generating markdown summaries.
  • [PROMPT_INJECTION]: The skill uses the $ARGUMENTS variable for project identification; no instructions to bypass security filters or override agent behavior were identified.
  • [DATA_EXFILTRATION]: No network operations or data exfiltration patterns were found. All file operations are restricted to the local filesystem environment.
  • [PROMPT_INJECTION]: Analysis of the indirect prompt injection surface: 1. Ingestion points: Reads various JSON files from data/cfo/, data/gtm/, data/product/, and data/engineering/. 2. Boundary markers: Data is loaded into the agent's context without specific delimiters or isolation instructions. 3. Capability inventory: Operations are limited to reading metrics and writing markdown reports to the data/cfo/board_decks/ directory. 4. Sanitization: No explicit validation or filtering of the ingested content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 12:08 AM
Security Audit — agent-trust-hub — board-deck