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
$1to 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