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 intask create,epic create, andsubtask createcommands, and the-c(content) flag in thecomment addcommand as seen inSKILL.mdandreferences/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
trekkerCLI 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