changelog-generator

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from git commit histories and style files. An attacker could craft a commit message containing instructions intended to manipulate the agent's behavior during generation. * Ingestion points: Git commit history logs and CHANGELOG_STYLE.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined in the provided documentation. * Capability inventory: The skill implies capabilities for reading git logs and writing to the local filesystem (e.g., CHANGELOG.md). * Sanitization: No mention of sanitization or validation of the commit message content before processing.
  • [NO_CODE]: The analyzed skill consists only of documentation and does not include any executable scripts, library dependencies, or configuration files that could be directly audited for malicious logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 05:13 AM