dev-docs
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- COMMAND_EXECUTION (LOW): The skill utilizes the 'Bash' tool to create directory structures and files. While 'Bash' is a high-privilege tool, the instructions are limited to standard file operations ('mkdir', 'write') for documentation purposes. No arbitrary command execution or shell injection vectors were identified.
- DATA_EXFILTRATION (SAFE): The skill only interacts with the local 'dev/active/' directory. No network operations or unauthorized file access patterns (such as reading SSH keys or environment files) are present.
- PROMPT_INJECTION (SAFE): The instructions do not contain attempts to override agent safety filters or system prompts. The 'task-name' variable is used for naming directories but does not influence the agent's core behavioral logic in a way that suggests injection risks.
- INDIRECT_PROMPT_INJECTION (LOW): The skill handles task descriptions which are inherently external data. While it lacks explicit sanitization, its primary function is documentation (Write/Read) which presents a low risk of influencing higher-privilege system decisions without human intervention.
Audit Metadata