team-security-review
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script,
discover-topic.sh, located in the skill's directory. This script handles logic for resolving the artifact path and is passed arguments that may be influenced by the agent's discovery process. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from repository files (e.g.,
1-task.md,8-plan.md) which can be controlled by external contributors and could contain instructions to divert the agent's behavior. - Ingestion points: Markdown files within the repository branch at
docs/plans/<id>/. - Boundary markers: There are no specified delimiters or 'ignore' instructions to isolate untrusted content from the agent's core instructions.
- Capability inventory: The skill has the ability to run shell commands, write new review files, and dispatch sub-agents.
- Sanitization: The skill does not define any validation or escaping mechanisms for the content read from the repository files before it is processed.
Audit Metadata