recoup-internal-consulting-metrics-updater
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to compute KPIs and generate visual dashboards, which creates a potential vulnerability surface for instructions embedded in that data to influence agent behavior.
- Ingestion points: The skill reads from pipeline records, client entities, and the workspace
AGENTS.mdfile to compute metrics. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the source data are provided in the skill body.
- Capability inventory: The skill is authorized to perform file system write operations to update
business/metrics/dashboard.htmland append dated snapshots to thebusiness/metrics/directory. - Sanitization: There are no specified sanitization or validation routines for the data processed from the pipeline or client records before it is used in computations or rendered into HTML.
Audit Metadata