inboundfy-especialista-changelog
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external and potentially untrusted data sources, such as raw product releases, pull request descriptions, and technical briefs. This creates an attack surface for indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: Material defined in the 'Entrada esperada' section of
SKILL.md, specifically pull requests and technical notes. - Boundary markers: The skill uses a structured workflow and mandates the use of specific templates defined in
REFERENCIA.mdto format the output. - Capability inventory: The skill's capabilities are restricted to text processing and invocation of internal framework tools like
inboundfy-copy-editorandinboundfy-validador-changelog. It lacks dangerous capabilities such as arbitrary network access or broad file system writes. - Sanitization: The instructions focus on content validation against internal project glossaries (
context/glossario.md) rather than technical sanitization of the input strings.
Audit Metadata