careful
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to read and follow project-specific lessons from a local file (
LESSONS.md) without validation. - Ingestion points: The skill reads external instructions from
LESSONS.mdin the project root as specified inSKILL.mdandAGENTS.md. - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to treat the content of
LESSONS.mdas untrusted data. - Capability inventory: The agent environment typically has shell execution capabilities (bash), as the skill is intended to monitor and execute potentially dangerous commands.
- Sanitization: Absent. The skill directs the agent to 'apply those project-specific lessons alongside the rules', granting the external file authoritative influence over agent behavior.
Audit Metadata