start
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script located at
${CLAUDE_PLUGIN_ROOT}/scripts/cli initwhen the user is identified as being in 'Builder Mode'. This is an environment initialization command specific to the forwward-teams platform. - [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect prompt injection surface by ingesting untrusted data from the local environment.
- Ingestion points: The agent is instructed to read contents from
README.md,package.json,pyproject.toml,CLAUDE.md, andAGENTS.mdto gather context about the user's project. - Boundary markers: There are no explicit instructions to use delimiters (e.g., XML tags or triple backticks) or warnings to the agent to ignore embedded instructions within these files.
- Capability inventory: The skill has the capability to execute the
${CLAUDE_PLUGIN_ROOT}/scripts/cli initcommand and trigger other skills based on the profile it builds. - Sanitization: There is no mention of sanitizing, validating, or filtering the data read from these project files before it is processed by the agent.
Audit Metadata