lcs-debug
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions.
- Ingestion points: The skill ingests user-provided reproduction steps, logs, error messages, and recent commits into the agent context in SKILL.md.
- Boundary markers: Absent; there are no instructions to use delimiters or specifically ignore instructions that might be embedded within the user-provided data.
- Capability inventory: The skill instructs the agent to execute reproduction commands (e.g., tests or scripts) and performs file system writes to the
.lcs/directory to manage work item states. - Sanitization: Absent; no validation, escaping, or filtering of external inputs is defined before the data is processed or written to disk.
Audit Metadata