careful
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it instructs the agent to read and follow instructions from an external file (LESSONS.md) located in the project workspace.
- Ingestion points: The agent is directed to read LESSONS.md from the project root and apply instructions tagged with "careful" (SKILL.md).
- Boundary markers: Absent. The instructions do not specify any delimiters or safety warnings to prevent the agent from obeying malicious commands embedded in the external file.
- Capability inventory: The agent has access to powerful tools including Bash, Write, Read, and Edit (SKILL.md).
- Sanitization: Absent. No filtering or validation is performed on the content of the external file before its instructions are integrated into the agent's behavior.
Audit Metadata