autocontext-consumer
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
autoctxCLI tool and standard utilities likecat. These commands are used for listing, showing, exporting, and importing knowledge data. - [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to read and process content from external files such as
playbook.mdandlessons.jsonwhich may contain untrusted instructions. - Ingestion points: Files located within the scenario directory (e.g.,
playbook.md,lessons.json,hints.md). - Boundary markers: None identified in the skill instructions to distinguish between data and instructions.
- Capability inventory: The skill allows the agent to execute shell commands (
cat,autoctx) and perform filesystem operations. - Sanitization: No sanitization or validation of the content of the knowledge files is mentioned.
Audit Metadata