disaster-prediction

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection (Category 8).
  • Ingestion points: The skill accepts user-supplied input via $ARGUMENTS and is explicitly instructed to "Investigate the entire codebase thoroughly," which involves reading arbitrary files from the local repository.
  • Boundary markers: The prompt does not utilize delimiters or specific instructions to ignore potential commands embedded within the analyzed data or code.
  • Capability inventory: The agent is granted capabilities to read any file in the project, create documentation in the docs/ folder, and write to a file in the user's home directory (~/.claude/projects/).
  • Sanitization: No validation or escaping of the ingested data is performed before it is processed by the agent.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes instructions to access a hidden directory in the user's home folder (~/.claude/projects/) to record telemetry. While this is used for tracking execution metadata, accessing internal configuration or project state directories is a sensitive operation that could be leveraged for data harvesting if combined with network exfiltration, though no network activity was detected in this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:56 AM
Security Audit — agent-trust-hub — disaster-prediction