pm-hybrid-prioritizer

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data (backlog items) which may contain untrusted content.
  • Ingestion points: Backlog items processed for scoring and ranking in SKILL.md.
  • Boundary markers: None defined. The skill does not explicitly use delimiters to isolate backlog content from its instructional logic.
  • Capability inventory: The skill interacts with $fortalece-api-routing-guide to resolve operations and includes a mutation_gate_v2 to control write access as specified in SKILL.md and agents/openai.yaml.
  • Sanitization: The instructions include a 'mutation gate' to prevent unauthorized writes, though no explicit sanitization of input text is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 08:31 PM
Security Audit — agent-trust-hub — pm-hybrid-prioritizer