dev-debug
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute environment setup commands like 'docker compose up -d' and version control operations such as 'git bisect'. These actions are directly related to its core function of local bug reproduction and investigation.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read data from external sources like '.konteksto/audit-register.md' and reproduction instructions provided by the user. While this creates an attack surface for indirect prompt injection due to the skill's high-privilege capabilities (Bash, file writes, and subagent spawning), no specific malicious triggers were identified. Ingestion points: .konteksto/audit-register.md and user-provided inputs. Boundary markers: Absent. Capability inventory: Bash, Read, Write, Edit, Agent. Sanitization: Absent.
Audit Metadata