Skills
Navigate
skills/hojiahao/cinefoundry/ad-brief-intake/Gen Agent Trust Hub

ad-brief-intake

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user requests to generate production briefs which are then used in shell commands and configuration files. \n
  • Ingestion points: User-supplied brief details in SKILL.md (Workflow steps 1-2). \n
  • Boundary markers: Absent for parameters in the cinefoundry command and brief.json output. \n
  • Capability inventory: Executes shell commands via cinefoundry project init and performs file-write operations. \n
  • Sanitization: Project id is validated as lowercase-dashed, but no sanitization is specified for title or brief fields. \n- [COMMAND_EXECUTION]: The skill executes the cinefoundry CLI tool with parameters derived from user input, which presents a command injection surface if the agent does not escape shell metacharacters in the title or brief fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 11:42 PM