charted-continue

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill determines its logic by reading and parsing content from a user-provided design document and project test files. This creates a surface for indirect prompt injection if those files contain instructions meant to divert the agent from its intended workflow.
  • Ingestion points: The skill reads ${designDocPath} in Step 1 and inspects the content of testFilePath in Step 5.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the document content as untrusted data or to ignore any embedded commands.
  • Capability inventory: The skill's primary capabilities include file system inspection and delegation to other specific skills within the charted-* suite.
  • Sanitization: No sanitization or structural validation is performed on the content of the ingested files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 09:26 AM
Security Audit — agent-trust-hub — charted-continue