qstack-ask-plan-open-questions
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is instructed to execute a local script located at
qstack/scripts/serve.shto verify the behavior and layout of generated HTML plans. This execution happens within the local repository environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from plan files and repository documentation to identify unresolved questions, which could potentially contain instructions aimed at influencing the agent's behavior.
- Ingestion points: Reads content from Markdown (
.md) and HTML (.html) plan files, as well as repository documentation and instruction files. - Boundary markers: The instructions do not specify the use of clear delimiters or boundary markers when reading and processing external plan content.
- Capability inventory: The skill possesses the ability to read and write to the file system (updating plan files) and execute shell commands (
serve.sh). - Sanitization: There is no evidence of sanitization or filtering applied to the content extracted from the plan files before it is used to generate questions or update the plan.
Audit Metadata