bagisto-documentation
Warn
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The
screenshots.mdfile contains hardcoded default credentials (admin@example.comandadmin123) for the Bagisto admin login. These are documented as the platform's standard default credentials for a freshly seeded store and are used to automate Playwright screenshot scripts. - [DYNAMIC_EXECUTION]: The
publishing.mdfile contains inline Python scripts executed via shell heredocs to perform validation tasks, such as checking for broken redirect targets and identifying orphaned pages in the documentation structure. - [COMMAND_EXECUTION]: The
SKILL.mdfile includes a shell command that performs a search for documentation repositories across the user's home directory (~), which is a broad file access pattern. - [INDIRECT_PROMPT_INJECTION]: The skill interacts with documentation markdown files which creates an attack surface for indirect prompt injection.
- Ingestion points: Documentation source files located in the
src/directory. - Boundary markers: The instructions do not define any delimiters or warnings to prevent the agent from executing instructions that may be embedded in the documentation text.
- Capability inventory: The skill has access to file system operations, shell command execution (git, find, grep, npm, php), and dynamic script execution (Python, Playwright).
- Sanitization: The skill does not implement any mechanisms to sanitize or filter documentation content before it is processed by the agent.
Audit Metadata