story-decisions

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed entirely of markdown documentation and procedural instructions, containing no executable scripts, binaries, or automated code.
  • [DATA_EXFILTRATION]: The skill instructs the agent to read and write story artifacts within a local project directory.
  • Evidence: The skill references paths like $MERIDIAN_FS_DIR/characters/, $MERIDIAN_FS_DIR/timeline/, and $MERIDIAN_FS_DIR/world/ for file operations.
  • This behavior is standard for the described narrative management use case and does not involve transmitting data to external domains.
  • [PROMPT_INJECTION]: The skill defines a process for 'mining' decisions from historical session transcripts, which represents a data ingestion surface.
  • Ingestion points: Session transcripts accessed via the meridian session command.
  • Boundary markers: The process uses HTML comments (<!-- decision: ... -->) to delimit extracted metadata from the main content.
  • Capability inventory: Reading session transcripts and writing annotations to project markdown files.
  • Sanitization: No specific sanitization or escaping mechanisms are described in the procedural guide.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 01:14 AM