inboundfy-growth-ferramentas-gratuitas
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (objectives, personas, and channel details) and uses it to generate or update local marketing briefs. This creates a surface where malicious instructions embedded in the user's request could potentially influence the agent's output or file-writing operations.
- Ingestion points: The skill expects objectives, IDs, personas, and channels as primary inputs in the
SKILL.mdworkflow. - Boundary markers: The skill uses markdown templates and YAML frontmatter (defined in
REFERENCIA.md), but lacks explicit instructions or delimiters to ignore potential commands embedded within the user-provided fields. - Capability inventory: The skill possesses file-write and update capabilities (e.g., updating existing briefs as per the 'Idempotência' section in
SKILL.md) and calls other internal skills likeinboundfy-setupandinboundfy-copy-edicao. - Sanitization: No explicit sanitization or filtering of user-provided content is defined before it is interpolated into the final output files.
Audit Metadata