recoup-internal-consulting-proposal-drafting
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes discovery transcripts and analyses which may contain untrusted data provided by third parties.
- Ingestion points: The skill reads external data in the form of "discovery transcript/analysis" as described in Step 1 of
SKILL.md. - Boundary markers: There are no explicit instructions to use delimiters or to ignore embedded instructions within the ingested transcripts to prevent them from influencing agent behavior.
- Capability inventory: The skill has the capability to read from and write to the local file system (e.g., saving proposals to the
02-proposals/directory and reading master templates). - Sanitization: No sanitization or validation of the input transcript content is specified before it is processed into a drafted proposal.
Audit Metadata