logvalet-my-week
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the
lvCLI tool (part of the logvalet suite) to fetch issue data from Backlog. This is the primary and intended behavior of the skill. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from an external source (Backlog issues).
- Ingestion points: Data enters the agent context through the output of the
lv issue listcommands defined inSKILL.md. - Boundary markers: Absent. The skill instructions do not specify any delimiters or provide instructions to the agent to disregard potential commands or instructions embedded within the retrieved task data.
- Capability inventory: The agent has access to the
bashtool as required for thelvcommand execution inSKILL.md. - Sanitization: Absent. No sanitization, escaping, or filtering of the retrieved issue content is performed before the agent formats the final output.
Audit Metadata