engineering-ai-engineer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from local project files (e.g.,
ai/memory-bank/requirements.md). This creates a vulnerability surface where malicious instructions embedded in these files could influence the agent's behavior or trigger unauthorized actions. - Ingestion points: The agent reads from
ai/memory-bank/requirements.mdandai/memory-bank/data-sources.mdas part of its requirements analysis phase (SKILL.md). - Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions within the ingested data.
- Capability inventory: The skill encourages the agent to execute shell commands like
cat,ls, andgrepto inspect the project environment (SKILL.md). - Sanitization: There is no evidence of sanitization, validation, or filtering performed on the content of the files before they are processed by the agent.
Audit Metadata