skills/openlair/dr-claw/ds-decision/Gen Agent Trust Hub

ds-decision

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements a secure interaction and tool discipline, explicitly forbidding direct shell execution and mandating the use of scoped environment tools such as bash_exec and artifact.git.
  • [SAFE]: Analysis of the skill body and templates revealed no signs of obfuscated content, hardcoded secrets, or malicious network operations.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it is instructed to ingest and process external sources including run artifacts, reports, and quest documents.
  • Ingestion points: Data enters the context via the reading of artifacts and documents specified in the Truth sources section of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or ignore-embedded-instructions warnings for the processed data.
  • Capability inventory: The skill utilizes powerful tools like bash_exec and artifact.complete_quest, which could be exploited if the agent follows instructions found in external data.
  • Sanitization: There is no evidence of validation or sanitization of ingested content before it influences decision-making.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 01:42 AM
Security Audit — agent-trust-hub — ds-decision