landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) due to its processing of untrusted project manifest and documentation files. * Ingestion points: The skill reads files such as 'README.md', 'package.json', 'pyproject.toml', 'Cargo.toml', 'go.mod', and 'CHANGELOG.md' during its workflow in 'references/readme-mode.md'. * Boundary markers: No explicit delimiters or instructions are used to prevent the agent from interpreting instructions that might be embedded within these external files. * Capability inventory: The skill executes shell commands for git operations ('git pull', 'git fetch', 'git stash') and file system tasks ('cp', overwriting 'README.md'). * Sanitization: There is no evidence of content sanitization or validation before the agent processes and interpolates data from these files.
- [COMMAND_EXECUTION]: The agent is instructed to run several shell commands to manage repository synchronization and file backups. Evidence includes 'git rev-parse', 'git fetch', 'git pull', 'git stash', and 'cp' commands defined in 'references/readme-mode.md'.
- [EXTERNAL_DOWNLOADS]: The 'git fetch origin' and 'git pull' commands mentioned in the workflow involve downloading data from a remote repository, which is a standard repository maintenance task but constitutes external data ingestion.
Audit Metadata