ask-parallel-auditor
Warn
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions in
SKILL.mddirect the agent to 'Generate shell commands to spawn specialized subagents'. This encourages the dynamic assembly and execution of shell commands, which can be vulnerable to command injection if file names or paths from the repository are not properly sanitized. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from the target repository.
- Ingestion points: Target files and directories identified in
SKILL.md(Workflow Step 1) and passed toscripts/spawn_workers.py. - Boundary markers: None identified; the instructions do not include delimiters or warnings to ignore instructions found within the audited files.
- Capability inventory: The skill has the capability to generate and execute shell commands and spawn subprocesses (as seen in
SKILL.mdandscripts/spawn_workers.py). - Sanitization: No sanitization or validation of the repository content is specified before it is processed or used to generate commands.
Audit Metadata