landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to manage repository state and ensure file safety during the README transformation process. Evidence: File references/readme-mode.md contains instructions for git fetch, git pull --rebase, git stash, and cp README.md README.backup.md to synchronize with remote and create backups.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes various project files that could contain untrusted content. 1. Ingestion points: As described in references/readme-mode.md, the agent reads README.md, package.json, pyproject.toml, Cargo.toml, go.mod, CHANGELOG.md, LICENSE, and documentation files. 2. Boundary markers: The instructions do not specify explicit delimiters or guardrails to prevent the agent from obeying instructions found within these project files. 3. Capability inventory: The skill is capable of executing shell commands (git) and modifying local files (README.md). 4. Sanitization: There is no evidence of sanitization or filtering applied to the content of the ingested files.
Audit Metadata