rpm-spec-generator

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data including packageName, version, buildRequires, and requires to generate RPM .spec files. This creates a vulnerability surface where an attacker could provide inputs containing malicious RPM macros or shell escapes that would be executed when rpmbuild or similar tools process the resulting file.
  • Ingestion points: SKILL.md defines an input schema that accepts various string and array parameters for package configuration.
  • Boundary markers: The provided documentation and examples do not include delimiters or instructions to ignore embedded commands in the input data.
  • Capability inventory: The skill is configured with Write and Bash tools, allowing it to create the files and potentially execute the build command (rpmbuild -ba).
  • Sanitization: There is no evidence of input validation or sanitization rules to prevent macro injection or shell metacharacters within the metadata fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 08:25 PM