ponytail-dev
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing external data sources which could contain malicious instructions.
- Ingestion points: The agent is instructed to process user-provided designs, bug reports, and existing software codebases as defined in
SKILL.md. - Boundary markers: The instructions do not specify technical delimiters or boundary markers to separate external input from the agent's core instructions.
- Capability inventory: The skill directs the agent to execute shell commands for builds, tests, and linting (found in
SKILL.md). - Sanitization: There are no instructions for sanitizing or validating external input before it is processed or used in shell commands.
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to use shell-based verification methods.
- The agent is directed to run "focused command, build, type check, linter" and "direct behavior check" to verify software changes (found in
SKILL.md). While standard for development tasks, this involves the execution of shell commands on the host environment.
Audit Metadata