qstack-loop-trequartista
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute arbitrary shell commands for builds, tests, and linters as defined within the repository it operates on. While these are standard development tasks, they involve executing instructions that may originate from the repository's configuration files.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data from implementation plans and repository source code.
- Ingestion points: Implementation plans (
plan.html,plan.md) and repository source code files are read into the agent context inSKILL.md. - Boundary markers: Absent; the instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill possesses the ability to execute shell commands (
tests,builds,linters) and delegate tasks to other agents. - Sanitization: Absent; there is no defined process for sanitizing or validating the content of external plans or code before processing.
Audit Metadata