geo-seo
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell commands like grep, find, ls, and cat to analyze project structure and content. These operations are used for site type and size detection and are consistent with the skill's diagnostic purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from the codebase being audited.
- Ingestion points: The skill reads source code and markdown files from the project directory during the detection and audit phases.
- Capability inventory: The skill uses Bash, Read, Glob, Grep, Write, and Edit tools, which could be exploited if malicious instructions in the audited files were followed by the agent.
- Boundary markers: There are no explicit instructions or delimiters defined to separate the audited content from the agent's operational logic.
- Sanitization: No sanitization or content filtering is applied to the data retrieved from the project files.
Audit Metadata