linear-metrics

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill passes user-provided identifiers like CYCLE_ID and PROJECT_ID directly to a Bash shell command. If these inputs contain shell metacharacters (e.g., semicolons or backticks), they could be used to execute unintended commands. Ingestion points: CYCLE_ID, PROJECT_ID, and TEAM_KEY parameters in SKILL.md. Boundary markers: Absent; no delimiters are used to wrap inputs. Capability inventory: Bash shell execution via 'linear-cli'. Sanitization: None provided within the skill instructions.
  • [Command Execution] (SAFE): The skill uses 'linear-cli' to fetch metrics as described in its metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM