lisa-repair-intake

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from multiple external platforms which creates an indirect prompt injection surface.
  • Ingestion points: Reads content from Notion, Confluence, Linear, GitHub, and JIRA.
  • Boundary markers: None provided; the agent is not instructed to use specific delimiters to distinguish between its instructions and the data being processed.
  • Capability inventory: The skill allows the agent to modify task states, file new fix tickets, and close items across the connected platforms.
  • Sanitization: There is no mention of validation or filtering for the external data before the agent performs operations based on that content.
  • [NO_CODE]: The skill is composed exclusively of natural language instructions and metadata in markdown format. It does not include scripts, binaries, or instructions to install third-party packages, which limits the risk of traditional software exploits.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 06:31 PM
Security Audit — agent-trust-hub — lisa-repair-intake