krillinai-cover

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a command using a CLI tool identified by the variable $KRILLINAI_CLI. This tool is used to perform the skill's primary function of generating cover images. The execution is scoped to a specific working directory and uses vendor-defined parameters.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts an external prompt via the $COVER_PROMPT variable which is passed directly to the CLI command. This creates a potential surface for indirect prompt injection if the content of the prompt is sourced from untrusted data.
  • Ingestion points: The --prompt argument in the SKILL.md file uses the $COVER_PROMPT environment variable.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the prompt content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill has the capability to execute the krillinai CLI tool and write output files to the local file system.
  • Sanitization: No sanitization or validation of the $COVER_PROMPT content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 10:39 PM