lgpd-md
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it is designed to ingest and act upon data from untrusted external sources.
- Ingestion points: According to
SKILL.md, the skill reads and parses content from user-specified local file paths and external URLs, includinglgpd.mdfiles, privacy policies, and sensitive internal documents such as RIPDs and DPAs. - Boundary markers: The instructions lack definitions for boundary markers or delimiters that would allow the agent to distinguish between its own system instructions and potentially malicious instructions embedded within the analyzed documents.
- Capability inventory: The skill possesses capabilities for local file system reads, local file writes (saving
lgpd.mdfiles and HTML reports), and network GET requests to fetch remote content. - Sanitization: There is no documented logic for sanitizing, escaping, or validating the text content of ingested files before it is processed by the LLM or interpolated into the generated HTML reports.
Audit Metadata