ai-team-orchestration
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for agents to read and follow external data sources such as repository instructions, PROJECT_BRIEF.md, and active issue trackers. This creates a surface for indirect prompt injection. 1. Ingestion points: identified in SKILL.md where agents are directed to read repository documentation and issues. 2. Boundary markers: the skill does not define explicit delimiters or instructions to ignore embedded malicious content in these external sources. 3. Capability inventory: the skill enables the agent to perform file writes (implementation), execute shell commands for testing/linting, and interact with pull requests. 4. Sanitization: there is no evidence of sanitization or content validation for the data ingested from the repository context.
- [COMMAND_EXECUTION]: The skill workflow involves executing standard development commands (e.g., npm test, pytest, npm run lint) to verify implementation changes. These are typical for development environments but represent a capability that could be targeted via the indirect prompt injection surface.
Audit Metadata