project-log
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through its summarization of workspace content.
- Ingestion points: The agent is instructed to read project files and the directory structure to populate the log.
- Boundary markers: None are defined to prevent the agent from following instructions found within the project files.
- Capability inventory: The skill can perform filesystem operations, specifically creating the
.docsdirectory and writing toproject-log.md. - Sanitization: No sanitization is performed on the data read from the project before it is written to the log file.
Audit Metadata