Morgan Westlee Lunt d44da81146 code-modernization: second-order injection fencing, path guards, scoped scaffolder agent ...

Addresses automated security review of the workflow conversion:

- Agent-produced text (rule specs, finding descriptions, dedup lists) is
  fenced as untrusted data when interpolated into downstream agent prompts,
  with embedded fence markers stripped so the fence can't be escaped;
  referees and judges are told to re-derive claims from the cited code.
- system/service/subdir names that land in filesystem paths inside prompts
  are validated against a strict pattern — traversal-shaped values throw
  before any agent spawns.
- Reimagine scaffolding now uses a dedicated 'scaffolder' agent with an
  explicit minimal tool list, a single-directory write scope, and the
  untrusted-content discipline extended to the generated spec/architecture
  docs it builds from (they derive from untrusted legacy code).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-06-09 19:40:58 +00:00

..

extract-rules.js

code-modernization: second-order injection fencing, path guards, scoped scaffolder agent

2026-06-09 19:40:58 +00:00

harden-scan.js

code-modernization: second-order injection fencing, path guards, scoped scaffolder agent

2026-06-09 19:40:58 +00:00

portfolio-assess.js

code-modernization: second-order injection fencing, path guards, scoped scaffolder agent

2026-06-09 19:40:58 +00:00

reimagine-scaffold.js

code-modernization: second-order injection fencing, path guards, scoped scaffolder agent

2026-06-09 19:40:58 +00:00