to-issue
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command
bd createwith arguments (--title,--description,--acceptance) synthesized from the conversation and codebase. If the source data contains shell metacharacters (like backticks or semicolons), it could lead to unintended command execution on the host machine. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface where untrusted data could influence agent actions.
- Ingestion points: The agent reads from the conversation context and explores the repository codebase (SKILL.md).
- Boundary markers: The instructions do not define delimiters or provide specific instructions to the agent to ignore potentially malicious instructions or shell control characters embedded in the codebase or chat.
- Capability inventory: The skill possesses the capability to execute shell commands via the
bdCLI tool (SKILL.md). - Sanitization: No sanitization, escaping, or validation logic is defined to protect the shell command arguments from malicious interpolation.
Audit Metadata