m11-ecosystem

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a shell command instruction in SKILL.md: grep -A 100 '^\\[dependencies\\]' Cargo.toml 2/dev/null | head -30 || echo "No Cargo.toml found". This pattern allows the agent to execute shell utilities and interact with the host filesystem to inject file contents into its runtime context.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of local file data.
  • Ingestion points: The skill reads the contents of the project's Cargo.toml file.
  • Boundary markers: No delimiters or warnings are used to separate the injected file content from the agent's instructions.
  • Capability inventory: The skill possesses the ability to execute shell commands (grep, head) and process the resulting output as context.
  • Sanitization: No validation, escaping, or filtering is performed on the data retrieved from the filesystem before it is processed by the model.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 11:44 AM