image-poster
Fail
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: In
SKILL.md(andREADME.md), the workflow instructs the agent to execute a shell commandnode "$OD_BIN" media generatein Step 2. This command interpolates user-provided data, including the image prompt and the output filename, directly into the command line. This pattern allows for command injection if a user provides input containing shell metacharacters such as;,&,|, or backticks. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user input to fulfill its primary function.
- Ingestion points: User-provided image descriptions and project metadata in
SKILL.mdStep 0 and Step 1. - Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the user input.
- Capability inventory: Shell execution capability via the
nodecommand inSKILL.mdStep 2. - Sanitization: Absent; the skill lacks any validation or escaping logic for the interpolated strings before they are passed to the shell.
Recommendations
- AI detected serious security threats
Audit Metadata