respira-site-audit
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill relies on a predefined set of internal tools (prefixed with
respira_) to perform site diagnostics and element-level updates within the WordPress builder environment.- [SAFE]: Analysis of the instructions and workflow revealed no evidence of command obfuscation, hidden URLs, persistence mechanisms, or unauthorized credential harvesting.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external WordPress pages, which presents a potential surface for indirect prompt injection attacks. - Ingestion points: Untrusted content is ingested from the target site via
respira_get_page_outlineand variousrespira_analyze_*tools (SKILL.md, Workflow section). - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded prompts within the audited page content.
- Capability inventory: The skill has the ability to modify site content using
respira_update_elementandrespira_apply_accessibility_fixes(SKILL.md, Rules section). - Sanitization: No explicit content sanitization or validation logic is specified in the provided instructions.
Audit Metadata