start
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local initialization script located at
${CLAUDE_PLUGIN_ROOT}/scripts/cli init. This is a routine operation for setting up the agent's environment within the platform.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and processes data from untrusted local project files to build a user profile and determine next steps. Malicious instructions embedded in these files could potentially influence the agent's recommendations. - Ingestion points: The agent reads content from
README.md,package.json,pyproject.toml,CLAUDE.md, andAGENTS.mdin the current working directory. - Boundary markers: No specific delimiters or instructions are provided to the agent to ignore potential malicious prompts within these files.
- Capability inventory: The skill has the ability to execute shell commands (
cli init) and read various files across the filesystem. - Sanitization: There is no evidence of content sanitization or validation performed on the data retrieved from the project files before it is used to influence agent state.
Audit Metadata