coverage-enhancer

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the local filesystem (source code and tests).
  • Ingestion points: The skill instructions direct the agent to read and parse source code and existing test files (SKILL.md).
  • Boundary markers: There are no instructions to use delimiters or ignore instructions found within the files being analyzed.
  • Capability inventory: The agent following these instructions has the capability to generate code and suggest the execution of shell commands like pytest, npm, and mvn (SKILL.md).
  • Sanitization: No sanitization or validation of the input file content is performed.
  • [NO_CODE]: The skill consists exclusively of instructional documentation and does not include any executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 10:20 PM