kiro-spec-status

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses a positional parameter $1 to define the target directory for specification files (e.g., .kiro/specs/$1/spec.json). This pattern is a vulnerability surface for path traversal; if not properly validated by the execution environment, an attacker could potentially access sensitive files outside the intended project directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from multiple external files including brief.md, requirements.md, design.md, and tasks.md. Malicious instructions embedded in these files could subvert the agent's behavior during the status analysis phase.
  • Ingestion points: Files located within the .kiro/specs/$1/ directory.
  • Boundary markers: None identified; file contents are processed directly without delimiters or 'ignore-instructions' guards.
  • Capability inventory: The skill can read file contents and generate status reports.
  • Sanitization: No validation or escaping of the parsed file content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 01:15 AM
Security Audit — agent-trust-hub — kiro-spec-status