skill-doctor
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute file system and text processing commands such as ls, basename, grep, and wc. These are used to verify file structures and check for specific patterns within the audited skill's files.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted content from the skill directory specified by the user. A malicious skill could contain instructions designed to mislead the auditing agent.
- Ingestion points: SKILL.md, reference files, and script files within the audited directory.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when reading external content.
- Capability inventory: The skill has access to Read, Grep, Glob, Bash, and Agent tools.
- Sanitization: No sanitization or escaping of the ingested file content is performed before it is analyzed by the agent.
Audit Metadata