activation-metrics
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a 'Codebase Audit' section that instructs the agent to scan the user's repository for activation-related events, setup flows, and status flags. This creates an attack surface where instructions embedded in the analyzed code could potentially influence agent actions.
- Ingestion points: Source code files within the user's repository.
- Boundary markers: No markers or explicit instructions to ignore content within strings or comments are provided.
- Capability inventory: The agent is tasked with file-reading and searching across the project structure.
- Sanitization: There are no instructions for sanitizing or filtering data extracted from the codebase.
- [EXTERNAL_DOWNLOADS]: The skill points to an external repository for additional auditing capabilities.
- Evidence: A link to https://github.com/SkeneTechnologies/skene-skills is provided as a recommended tool for generating growth manifests.
- Note: This reference targets a repository owned by the skill's author ('skenetechnologies').
Audit Metadata