ai-risk-assessment
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted data such as feature tickets, system context descriptions, and architectural documentation to perform risk assessments. This creates a surface where malicious instructions embedded in analyzed project data could attempt to influence the agent's report or conclusions.
- Ingestion points: The skill reads external data from sources like
feature-ticket.jsonand system context files to populate the risk register. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' wrappers when processing the untrusted system data.
- Capability inventory: The skill is authorized to use
write_file,create_file, andexecute_commandto generate its outputs and potentially validate configurations. - Sanitization: There is no evidence of automated sanitization or validation of the input text content before it is incorporated into the assessment process.
Audit Metadata