llms-txt-generator
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
python llmtxt-generator.pyfrom the repository root after instructing the agent to modify the script's source code. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from local files and directory structures to modify executable logic.
- Ingestion points:
apps/web/public/llms.txtand theapps/directory structure. - Boundary markers: Absent; there are no instructions to ignore or delimit embedded instructions within the source files.
- Capability inventory: The agent can perform file writes to
llmtxt-generator.pyand execute shell commands (python). - Sanitization: Absent; the skill does not specify validation or sanitization of the content extracted from the scanned files before using it to update the Python script.
Audit Metadata