recoup-internal-consulting-quarterly-value-review
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes client delivery logs and notes which are considered untrusted data sources that could influence the agent's behavior during report generation.
- Ingestion points: The skill reads notes and logs from
clients/{client}/04-delivery/(SKILL.md). - Boundary markers: There are no instructions to use delimiters or ignore instructions embedded within the ingested client notes.
- Capability inventory: The skill has file-write capabilities to the
clients/{client}/05-retention/directory and theAGENTS.mdfile (SKILL.md). - Sanitization: The skill does not specify any validation, filtering, or escaping for the content pulled from client logs before using it to generate reviews or update dashboards.
Audit Metadata