seo-geo-optimisation
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requests external data ingestion via the "Current content" input field for auditing and optimization purposes. This represents a potential surface for indirect prompt injection if the provided text contains hidden instructions.
- Ingestion points:
SKILL.md(Required Input #7: "Current content"). - Boundary markers: Absent; the skill does not instruct the agent to use delimiters or specific ignore-rules for the ingested content.
- Capability inventory: None; the skill's operations are limited to text analysis and markdown generation, with no access to system commands, file writes, or network tools.
- Sanitization: Absent.
- [NO_CODE]: The skill contains no executable code, shell scripts, or external software dependencies. It functions purely as a set of logical instructions for the AI agent.
Audit Metadata