forge-review
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
forge-memoryCLI tool to perform searches, log activities, consolidate data, and synchronize state. These operations appear to be part of the vendor's internal toolset for project context management. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks (Category 8).
- Ingestion points: The agent ingests data from external artifacts provided by the user and from the
.forge/memory/MEMORY.mdfile. - Boundary markers: No specific boundary markers or 'ignore' instructions are present to prevent the agent from obeying instructions hidden within the analyzed artifacts.
- Capability inventory: The skill has the ability to read local files and execute shell commands via the
forge-memoryutility. - Sanitization: The skill does not implement sanitization or escaping for the artifact content or its metadata before using them in command-line arguments for
forge-memory log.
Audit Metadata