comet-tweak
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to run various shell commands, including local workflow management tools (comet, openspec) and standard development tools (npm, mvn).
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from external sources and using it to determine its next steps, which presents a vulnerability to indirect prompt injection.
- Ingestion points: The agent reads content from project-level files like proposal.md, design.md, tasks.md, and spec files, as well as dynamic instruction JSON from the openspec CLI tool.
- Boundary markers: There are no explicit instructions to treat the ingested content as data only or to ignore instructions embedded within those files.
- Capability inventory: The skill has the capability to execute shell commands and modify the file system via multiple sub-skills.
- Sanitization: The skill does not describe any validation or sanitization process for the data ingested from the project files or tool outputs.
Audit Metadata