skills/oakoss/agent-skills/trekker/Gen Agent Trust Hub

trekker

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted task descriptions, epic goals, and comments which could be used to influence agent behavior.
  • Ingestion points: Data enters the system via the -d (description) flag in task create, epic create, and subtask create commands, and the -c (content) flag in the comment add command as seen in SKILL.md and references/commands.md.
  • Boundary markers: The instructions do not define delimiters or specific warnings for the agent to ignore instructions embedded within the retrieved task metadata or comments.
  • Capability inventory: The agent has the ability to execute trekker CLI commands to modify the local task database and view project history.
  • Sanitization: There is no mention of input validation or sanitization for the text strings provided to the CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:51 AM
Security Audit — agent-trust-hub — trekker