project-intake

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external project files which may contain embedded instructions. Ingestion points: HANDOFF.md, README, and files within HANDOFF-ARCHIVE/. Boundary markers: No specific delimiters or boundary instructions are provided for processed content. Capability inventory: The agent can execute git commands and write updates to project files. Sanitization: The instructions explicitly mandate desensitization (excluding API keys and PII) when updating documents.
  • [COMMAND_EXECUTION]: The skill uses standard version control commands such as git init, git commit, and git log. These operations are restricted to project lifecycle management and do not involve arbitrary command execution from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 09:28 PM
Security Audit — agent-trust-hub — project-intake