ecology-letters
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external resource files (
../../resources/source-basis.mdand../../resources/official-source-map.md) to verify submission requirements. While these are likely internal project files, they represent an ingestion point for untrusted data if those files are modified by external processes. - Ingestion points: Files located at
../../resources/source-basis.mdand../../resources/official-source-map.mdas specified in the 'Official-submission checklist' section. - Boundary markers: Absent; there are no specific delimiters or instructions to the agent to ignore embedded commands within these external files.
- Capability inventory: No capabilities for file writing, network exfiltration, or command execution were detected within the skill scripts or instructions.
- Sanitization: Absent; the skill does not specify validation or filtering for the content retrieved from these resources.
- [SAFE]: The skill references well-known and trusted academic services including Wiley, Dryad, Zenodo, and bioRxiv for data archiving and preprint policies. These references are documented neutrally as part of standard scientific publishing workflows.
Audit Metadata