alterlab-cdm-postproduction
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to autonomously 'Read existing project files for context' and 'Search the web'. These ingestion points process untrusted data (such as external edit notes, director feedback, or web content) which could contain malicious instructions designed to manipulate the agent's behavior.
- Ingestion points: SKILL.md (Workflow and Media Management sections) specifies reading project files, edit notes, and director feedback from the project directory.
- Boundary markers: The instructions do not define delimiters or specific safety instructions to isolate and ignore potentially malicious content embedded within the files it reads.
- Capability inventory: The skill allows the agent to write files directly to the project directory (e.g.,
{project}-post-schedule.md,{project}-export-settings.md) and perform web searches. - Sanitization: There is no mention of sanitizing, escaping, or validating the content of the project files before they are processed by the agent.
Audit Metadata