sra-config-analysis-shared
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, including customer organization configurations, knowledge articles, and interaction transcripts, which could potentially contain adversarial instructions designed to influence the agent's behavior.
- Ingestion points: Data is collected via mcp-adaptor tools (query, read_file, search) and through direct user input in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or guidelines to ignore instructions embedded within the content being analyzed.
- Capability inventory: The skill has access to powerful tools including Bash, Write, Edit, and various mcp-adaptor query functions.
- Sanitization: There is no mention of sanitizing or escaping the external content before it is processed for analysis.
Audit Metadata